19 Oct 2026 to 26 Oct 2026. What the grams proved of the catalog this window, per artifact and hardware class. Lineage is from the catalog; every number is a signed measurement or a count of them, and a gram count is a verified floor.
The order a season proves things in: the number every other number is compared to comes first.
A class is os · arch · card class · RAM band. A number proved on one says nothing about another.
Listed by held outcomes. Downloads, likes and popularity do not appear on this page, because nobody signs them.
the engine has no loader for this architecture — a release changes that, never a clock
the ref, or the quant asked of it, is not published upstream
the ref, or the quant asked of it, is not published upstream
the ref, or the quant asked of it, is not published upstream
the ref, or the quant asked of it, is not published upstream
the ref, or the quant asked of it, is not published upstream
the ref, or the quant asked of it, is not published upstream
the ref, or the quant asked of it, is not published upstream
the ref, or the quant asked of it, is not published upstream
the ref, or the quant asked of it, is not published upstream
the ref, or the quant asked of it, is not published upstream
the ref, or the quant asked of it, is not published upstream
the ref, or the quant asked of it, is not published upstream
the engine has no loader for this architecture — a release changes that, never a clock
the engine has no loader for this architecture — a release changes that, never a clock
the engine has no loader for this architecture — a release changes that, never a clock
the engine has no loader for this architecture — a release changes that, never a clock
the engine has no loader for this architecture — a release changes that, never a clock
the engine has no loader for this architecture — a release changes that, never a clock
the engine has no loader for this architecture — a release changes that, never a clock
the ref, or the quant asked of it, is not published upstream
the engine has no loader for this architecture — a release changes that, never a clock
the engine has no loader for this architecture — a release changes that, never a clock
the engine has no loader for this architecture — a release changes that, never a clock
refusals are signed facts about (artifact, class): gated, unloadable, or absent upstream. They are coverage of a kind -- the fleet learned it once -- and they sink the cell to the back of every gram of that class. A refusal lifts when its season closes and the engine that refused has moved on.
carried forward — no gram of this class reported in the latest aggregate
carried forward — no gram of this class reported in the latest aggregate
carried forward — no gram of this class reported in the latest aggregate
cost is operational: medians of node-reported pull/probe clocks per hardware class and engine, with sample counts. It is not a measurement of any model and is never ranked.
demand is tokens produced per artifact per class, from signed throughput observations; it orders depth, never existence.
Cohort 0 · Lead member, rung 0 · 21
depth-anything · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: vision.spatial
Efficient-Large-Model · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: image.generate
facebook · vendor build
held on Linux · x86-64 · no GPU · 32 GiB: translate.as, translate.bn, translate.gu, translate.hi, translate.kn, translate.ml, translate.mr, translate.or, translate.pa, translate.ta, translate.te, translate.text, translate.ur
facebook · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: vision.count
google · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.am, lang.as, lang.bn, lang.en, lang.es, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.ne, lang.nl, lang.or, lang.pa, lang.ru, lang.si, lang.sw, lang.ta, lang.te, lang.ur, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 282.3k tokens across the network
google · vendor build
held on Linux · x86-64 · no GPU · 32 GiB: translate.as, translate.bn, translate.gu, translate.hi, translate.kn, translate.ml, translate.mr, translate.or, translate.pa, translate.ta, translate.text
bartowski · quantization of krutrim-ai-labs/Krutrim-2-instruct
held on Linux · x86-64 · NVIDIA · 32 GiB: code.write, instruct.follow, lang.bn, lang.en, lang.gu, lang.kn, lang.ml, lang.mr, lang.pa, lang.ta, lang.te, output.long, output.schema, research.synthesize, structured_output
served 3.2k tokens across the network
bartowski · quantization of sarvamai/sarvam-1
held on Linux · x86-64 · NVIDIA · 32 GiB: lang.bn, lang.hi, lang.kn, lang.ml, lang.mr, output.long, output.schema, structured_output
served 12.5k tokens across the network
ibm-granite · vendor build
held on Linux · x86-64 · no GPU · 32 GiB: code.write, instruct.follow, lang.en, lang.ta, output.long, output.schema, structured_output, tools, tools.call, tools.loop_ends, tools_loop_terminated
served 7.2k tokens across the network
mradermacher · quantization of ai4bharat/Airavata
held on Linux · x86-64 · NVIDIA · 32 GiB: instruct.follow, lang.en, lang.hi, output.long
served 26.3k tokens across the network
QuantFactory · quantization of sarvamai/OpenHathi-7B-Hi-v0.1-Base
served 155.7k tokens across the network
Qwen · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: code.write, faithful_tool_result, instruct.follow, lang.en, output.schema, structured_output, tools, tools.call, tools.faithful, tools.loop_ends, tools_loop_terminated
served 237.5k tokens across the network
Qwen · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.en, lang.ta, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.multi_hop
served 46.4k tokens across the network
unsloth · quantization of google/functiongemma-270m-it
held on Linux · x86-64 · no GPU · 32 GiB: lang.en, output.long, output.schema, structured_output
served 34.7k tokens across the network
unsloth · quantization of google/gemma-3-270m-it
held on Linux · x86-64 · no GPU · 32 GiB: code.write, lang.bn, lang.en, output.schema, structured_output
served 15.5k tokens across the network
unsloth · quantization of google/gemma-4-E2B-it
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.ar, lang.as, lang.bn, lang.de, lang.en, lang.es, lang.fa, lang.fr, lang.gu, lang.he, lang.hi, lang.id, lang.it, lang.ja, lang.kn, lang.ko, lang.ml, lang.mr, lang.ms, lang.ne, lang.nl, lang.or, lang.pa, lang.pl, lang.pt, lang.si, lang.ta, lang.te, lang.th, lang.tr, lang.uk, lang.ur, lang.vi, lang.zh, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 512.1k tokens across the network
unsloth · quantization of microsoft/Phi-4-mini-instruct
held on Linux · x86-64 · NVIDIA · 32 GiB: code.write, instruct.follow, lang.en, lang.hi, output.long, output.schema, research.synthesize, structured_output
served 17.6k tokens across the network
pyannote · vendor build
speechbrain · vendor build
stabilityai · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: image.generate
refused on Windows · x86-64 · Intel GPU · 16 GiB — unloadable, by 1 gram
THUDM · vendor build
refused on Linux · x86-64 · NVIDIA · 32 GiB — unloadable, by 1 gram
Cohort 1 · Lead member's ladder · 34
facebook · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: audio.music
ggml-org · quantization of google/embeddinggemma-300m
held on Linux · x86-64 · no GPU · 32 GiB: embed.vector
Qwen · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.en, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.multi_hop
served 20.9k tokens across the network
unsloth · quantization of google/functiongemma-270m-it
held on Linux · x86-64 · no GPU · 32 GiB: lang.en, lang.hi, output.schema, structured_output
served 15.1k tokens across the network
unsloth · quantization of google/gemma-3-270m-it
held on Linux · x86-64 · no GPU · 32 GiB: code.write, lang.en, output.schema, structured_output
served 2.3k tokens across the network
unsloth · quantization of google/gemma-4-E2B-it
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.am, lang.as, lang.bn, lang.en, lang.es, lang.gu, lang.hi, lang.ja, lang.kn, lang.ml, lang.mr, lang.ne, lang.nl, lang.or, lang.pa, lang.ru, lang.si, lang.sw, lang.ta, lang.te, lang.ur, lang.zh, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 19.5k tokens across the network
unsloth · quantization of microsoft/Phi-4-mini-instruct
held on Linux · x86-64 · NVIDIA · 32 GiB: code.write, instruct.follow, lang.en, lang.ta, output.long, output.schema, research.synthesize, structured_output
served 7.1k tokens across the network
unsloth · quantization of google/functiongemma-270m-it
held on Linux · x86-64 · no GPU · 32 GiB: output.schema, structured_output
served 10.4k tokens across the network
unsloth · quantization of google/gemma-3-270m-it
held on Linux · x86-64 · no GPU · 32 GiB: code.write, lang.en, output.schema, structured_output
served 5.2k tokens across the network
unsloth · quantization of microsoft/Phi-4-mini-instruct
held on Linux · x86-64 · NVIDIA · 32 GiB: code.write, lang.bn, lang.en, output.long, output.schema, structured_output
served 12.4k tokens across the network
unsloth · quantization of Qwen/Qwen3-4B
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.en, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools_loop_terminated
served 152.6k tokens across the network
Qwen · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.en, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated
served 16.8k tokens across the network
unsloth · quantization of google/embeddinggemma-300m
held on Linux · x86-64 · no GPU · 32 GiB: embed.vector
unsloth · quantization of google/functiongemma-270m-it
held on Linux · x86-64 · no GPU · 32 GiB: code.reason, lang.en, output.long, output.schema, structured_output
served 6.2k tokens across the network
unsloth · quantization of google/gemma-3-270m-it
held on Linux · x86-64 · no GPU · 32 GiB: code.write, lang.en, output.long, output.schema, structured_output
served 4.6k tokens across the network
unsloth · quantization of microsoft/Phi-4-mini-instruct
held on Linux · x86-64 · NVIDIA · 32 GiB: code.write, instruct.follow, lang.bn, lang.en, lang.hi, lang.ml, output.long, output.schema, research.synthesize, structured_output
served 4.4k tokens across the network
microsoft · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: code.write, instruct.follow, lang.en, output.long, output.schema, research.synthesize, structured_output
sarvamai · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: lang.bn, lang.gu, lang.hi, lang.mr, lang.pa, output.long, output.schema, structured_output
unsloth · quantization of google/embeddinggemma-300m
held on Linux · x86-64 · no GPU · 32 GiB: embed.vector
unsloth · quantization of google/functiongemma-270m-it
held on Linux · x86-64 · no GPU · 32 GiB: lang.bn, lang.en, lang.hi, output.schema, structured_output
served 12.3k tokens across the network
unsloth · quantization of google/gemma-3-270m-it
held on Linux · x86-64 · no GPU · 32 GiB: code.write, lang.en, output.schema, structured_output
served 3.4k tokens across the network
unsloth · quantization of google/gemma-4-E2B-it
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.am, lang.as, lang.bn, lang.en, lang.es, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.ne, lang.nl, lang.or, lang.pa, lang.ru, lang.si, lang.sw, lang.ta, lang.te, lang.ur, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 22.5k tokens across the network
unsloth · quantization of microsoft/Phi-4-mini-instruct
held on Linux · x86-64 · NVIDIA · 32 GiB: code.write, instruct.follow, lang.en, lang.hi, lang.ml, output.long, output.schema, structured_output
served 5.6k tokens across the network
unsloth · quantization of google/functiongemma-270m-it
held on Linux · x86-64 · no GPU · 32 GiB: output.schema, structured_output
served 9.6k tokens across the network
unsloth · quantization of google/gemma-3-270m-it
held on Linux · x86-64 · no GPU · 32 GiB: code.write, lang.en, output.schema, structured_output
served 5.6k tokens across the network
unsloth · quantization of meta-llama/Llama-3.2-3B-Instruct
held on Linux · x86-64 · NVIDIA · 32 GiB: lang.en
served 10.2k tokens across the network
unsloth · quantization of microsoft/Phi-4-mini-instruct
held on Linux · x86-64 · NVIDIA · 32 GiB: code.write, lang.en, output.long, output.schema, structured_output
served 27.9k tokens across the network
unsloth · quantization of Qwen/Qwen3-4B
served 127.6k tokens across the network
Qwen · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.en, lang.hi, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated
served 41.8k tokens across the network
unsloth · quantization of google/embeddinggemma-300m
held on Linux · x86-64 · no GPU · 32 GiB: embed.vector
unsloth · quantization of google/gemma-3-270m-it
held on Linux · x86-64 · no GPU · 32 GiB: output.schema, structured_output
served 9.4k tokens across the network
unsloth · quantization of google/gemma-4-E2B-it
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.am, lang.as, lang.bn, lang.en, lang.es, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.ne, lang.nl, lang.or, lang.pa, lang.ru, lang.si, lang.sw, lang.ta, lang.te, lang.ur, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 37.1k tokens across the network
kokoro · vendor build
held on Linux · x86-64 · no GPU · 32 GiB: audio, audio.out, lang.en
UsefulSensors · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: audio, audio.in, lang.en
Cohort 2 · Other vendor members · 36
depth-anything · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: vision.spatial
facebook · vendor build
held on Linux · x86-64 · no GPU · 32 GiB: translate.as, translate.bn, translate.gu, translate.hi, translate.kn, translate.ml, translate.mr, translate.or, translate.pa, translate.ta, translate.te, translate.text, translate.ur
google · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.am, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.nl, lang.pa, lang.ru, lang.sw, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 5.7k tokens across the network
bartowski · quantization of sarvamai/sarvam-m
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, lang.bn, lang.en, lang.hi, lang.kn, lang.ml, lang.mr, lang.pa, lang.ta, lang.te, output.long, reason.channel, research.synthesize, thinking
served 40.3k tokens across the network
ggml-org · quantization of google/gemma-3-1b-it
held on Linux · x86-64 · no GPU · 32 GiB: code.write, instruct.follow, lang.en, lang.gu, lang.hi, lang.mr, lang.te, output.long, output.schema, structured_output
served 5.4k tokens across the network
unsloth · quantization of google/gemma-4-12B-it
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.am, lang.bn, lang.en, lang.gu, lang.ha, lang.hi, lang.kn, lang.ml, lang.mr, lang.nl, lang.pa, lang.ru, lang.sw, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 10.5k tokens across the network
unsloth · quantization of google/gemma-4-31B-it
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.am, lang.as, lang.bn, lang.en, lang.es, lang.gu, lang.ha, lang.hi, lang.kn, lang.ml, lang.mr, lang.ne, lang.nl, lang.or, lang.pa, lang.ru, lang.si, lang.sw, lang.ta, lang.te, lang.ur, lang.yo, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 12.3k tokens across the network
unsloth · quantization of google/gemma-4-E4B-it
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read
served 4.0k tokens across the network
unsloth · quantization of LiquidAI/LFM2.5-1.2B-Instruct
held on Linux · x86-64 · no GPU · 32 GiB: code.reason, code.write, faithful_tool_result, lang.en, output.long, output.schema, structured_output, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated
served 18.3k tokens across the network
unsloth · quantization of microsoft/Phi-4-reasoning-plus
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, lang.bn, lang.en, lang.hi, lang.kn, lang.ml, lang.mr, lang.pa, lang.ta, lang.te, output.long, output.schema, research.synthesize, structured_output
served 28.4k tokens across the network
unsloth · quantization of Qwen/Qwen3.5-0.8B
held on Linux · x86-64 · no GPU · 32 GiB: code.write, output.schema, reason.channel, structured_output, thinking, tools, tools.call
served 83.7k tokens across the network
hunyuanvideo-community · quantization of a vendor base
Lightricks · vendor build
refused on Linux · x86-64 · NVIDIA · 32 GiB — unloadable, by 1 gram
openai · vendor build
held on Linux · x86-64 · no GPU · 32 GiB: audio, audio.in, lang.en
openai · vendor build
held on Linux · x86-64 · no GPU · 32 GiB: audio, audio.in, lang.en, lang.hi, lang.mr, lang.ne, lang.ta, lang.ur
facebook · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: audio.music
Qwen · vendor build
held on Linux · x86-64 · no GPU · 32 GiB: code.reason, code.write, instruct.follow, lang.en, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call
served 15.2k tokens across the network
Qwen · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.bn, lang.en, lang.hi, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.multi_hop
served 18.9k tokens across the network
unsloth · quantization of google/gemma-4-12B-it
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.am, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.nl, lang.pa, lang.ru, lang.sw, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 11.0k tokens across the network
unsloth · quantization of google/gemma-4-26B-A4B-it
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.am, lang.as, lang.bn, lang.en, lang.es, lang.gu, lang.ha, lang.hi, lang.kn, lang.ml, lang.mr, lang.ne, lang.nl, lang.or, lang.pa, lang.ru, lang.si, lang.sw, lang.ta, lang.te, lang.ur, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 9.4k tokens across the network
unsloth · quantization of google/gemma-4-E4B-it
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.am, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.nl, lang.pa, lang.ru, lang.sw, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 5.1k tokens across the network
unsloth · quantization of Qwen/Qwen3.5-0.8B
held on Linux · x86-64 · no GPU · 32 GiB: reason.channel, thinking, tools, tools.call
served 15.5k tokens across the network
bartowski · quantization of meta-llama/Llama-3.2-1B-Instruct
held on Linux · x86-64 · no GPU · 32 GiB: code.write, faithful_tool_result, instruct.follow, lang.en, output.long, output.schema, structured_output, tools, tools.call, tools.faithful, tools.loop_ends, tools_loop_terminated
served 3.5k tokens across the network
google · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 7.2k tokens across the network
lmstudio-community · quantization of google/gemma-3-1b-it
held on Linux · x86-64 · no GPU · 32 GiB: code.write, instruct.follow, lang.bn, lang.en, lang.hi, lang.mr, lang.te, output.long, output.schema, structured_output
served 2.6k tokens across the network
unsloth · quantization of Qwen/Qwen3.5-0.8B
held on Linux · x86-64 · no GPU · 32 GiB: instruct.follow, lang.en, reason.channel, thinking, tools, tools.call
served 16.8k tokens across the network
Qwen · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: code.write, faithful_tool_result, instruct.follow, lang.en, lang.hi, lang.kn, lang.ml, lang.ta, lang.te, output.long, output.schema, structured_output, tools, tools.call, tools.faithful, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 3.9k tokens across the network
Qwen · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: code.write, faithful_tool_result, instruct.follow, lang.bn, lang.en, lang.hi, lang.kn, lang.mr, lang.pa, lang.te, output.long, output.schema, structured_output, tools, tools.call, tools.faithful, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 2.4k tokens across the network
unsloth · quantization of google/gemma-4-12B-it
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.am, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.nl, lang.pa, lang.ru, lang.sw, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated
served 9.1k tokens across the network
unsloth · quantization of google/gemma-4-E4B-it
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.am, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.nl, lang.pa, lang.ru, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 5.1k tokens across the network
bartowski · quantization of meta-llama/Llama-3.2-1B-Instruct
held on Linux · x86-64 · no GPU · 32 GiB: code.write, instruct.follow, lang.en, lang.kn, lang.te, output.long, output.schema, structured_output, tools, tools.call, tools.loop_ends, tools_loop_terminated
served 3.1k tokens across the network
lmstudio-community · quantization of google/gemma-3-1b-it
held on Linux · x86-64 · no GPU · 32 GiB: code.write, instruct.follow, lang.bn, lang.en, lang.gu, lang.hi, lang.te, output.long, output.schema, structured_output
served 2.6k tokens across the network
unsloth · quantization of google/gemma-4-12B-it
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 7.5k tokens across the network
unsloth · quantization of google/gemma-4-E4B-it
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 3.9k tokens across the network
UsefulSensors · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: audio, audio.in, lang.en
Wan-AI · vendor build
held on Linux · x86-64 · NVIDIA · 32 GiB: video.generate
Cohort 3 · Derivatives · 28
hugging-quants · derivative of meta-llama/Llama-3.2-1B-Instruct
held on Linux · x86-64 · no GPU · 32 GiB: lang.en, output.long, output.schema, structured_output
served 10.6k tokens across the network
lm-kit · derivative of a vendor base
held on Linux · x86-64 · no GPU · 32 GiB: embed.vector
mingxilei · derivative of a vendor base
held on Linux · x86-64 · no GPU · 32 GiB: output.schema, structured_output
served 373 tokens across the network
mradermacher · derivative of acon96/Home-FunctionGemma-270m
served 10.9k tokens across the network
Mungert · derivative of a vendor base
held on Linux · x86-64 · no GPU · 32 GiB: lang.bn, lang.en, output.schema, structured_output
served 8.0k tokens across the network
victor · derivative of unsloth/functiongemma-270m-it
held on Linux · x86-64 · no GPU · 32 GiB: output.schema, reason.channel, structured_output, thinking
served 6.1k tokens across the network
cduk · derivative of google/embeddinggemma-300m
held on Linux · x86-64 · no GPU · 32 GiB: embed.vector
lm-kit · derivative of a vendor base
held on Linux · x86-64 · no GPU · 32 GiB: embed.vector
mingxilei · derivative of a vendor base
held on Linux · x86-64 · no GPU · 32 GiB: code.write, output.schema, structured_output
served 13.2k tokens across the network
mradermacher · derivative of acon96/Home-FunctionGemma-270m
served 13.4k tokens across the network
Mungert · derivative of a vendor base
held on Linux · x86-64 · no GPU · 32 GiB: lang.en, lang.hi, output.schema, structured_output
served 14.7k tokens across the network
segmind · derivative of a vendor base
held on Linux · x86-64 · NVIDIA · 32 GiB: image.generate
mradermacher · derivative of acon96/Home-FunctionGemma-270m
served 9.1k tokens across the network
Mungert · derivative of a vendor base
held on Linux · x86-64 · no GPU · 32 GiB: lang.hi, output.schema, structured_output
served 7.8k tokens across the network
cduk · derivative of google/embeddinggemma-300m
held on Linux · x86-64 · no GPU · 32 GiB: embed.vector
lm-kit · derivative of a vendor base
held on Linux · x86-64 · no GPU · 32 GiB: embed.vector
mingxilei · derivative of a vendor base
held on Linux · x86-64 · no GPU · 32 GiB: code.write, output.schema, structured_output
served 6.8k tokens across the network
mradermacher · derivative of acon96/Home-FunctionGemma-270m
served 13.9k tokens across the network
Mungert · derivative of a vendor base
held on Linux · x86-64 · no GPU · 32 GiB: lang.bn, lang.en, lang.hi, output.schema, structured_output
served 10.8k tokens across the network
lm-kit · derivative of a vendor base
held on Linux · x86-64 · no GPU · 32 GiB: embed.vector
mingxilei · derivative of a vendor base
held on Linux · x86-64 · no GPU · 32 GiB: code.reason, code.write, output.schema, structured_output
served 13.6k tokens across the network
mradermacher · derivative of acon96/Home-FunctionGemma-270m
served 13.6k tokens across the network
Mungert · derivative of a vendor base
held on Linux · x86-64 · no GPU · 32 GiB: lang.bn, lang.en, lang.hi, output.schema, structured_output
served 15.6k tokens across the network
mradermacher · derivative of acon96/Home-FunctionGemma-270m
served 9.7k tokens across the network
mradermacher · derivative of acon96/Home-FunctionGemma-270m
served 12.8k tokens across the network
Mungert · derivative of a vendor base
held on Linux · x86-64 · no GPU · 32 GiB: lang.bn, lang.hi, output.schema, structured_output
served 11.4k tokens across the network
zai-org · derivative of a vendor base
refused on Linux · x86-64 · NVIDIA · 32 GiB — unloadable, by 1 gram
zai-org · derivative of a vendor base
Measured, not in the catalog · 48
unknown publisher
unknown publisher
held on hardware not stated in the signed payload: tools
served 359.2k tokens across the network
unknown publisher
held on hardware not stated in the signed payload: tools
served 36.4k tokens across the network
unknown publisher
held on hardware not stated in the signed payload: tools
served 48.8k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 11.4k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read
served 5.1k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 13.2k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 8.3k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 13.1k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 8.3k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 9.1k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.write, faithful_tool_result, instruct.follow, lang.en, lang.ml, lang.te, output.long, output.schema, structured_output, tools, tools.call, tools.faithful, tools.loop_ends, tools_loop_terminated
served 3.6k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.write, faithful_tool_result, instruct.follow, lang.en, lang.hi, lang.kn, output.long, output.schema, research.synthesize, structured_output, tools, tools.call, tools.faithful, tools.loop_ends, tools_loop_terminated
served 4.0k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, lang.en, lang.kn, output.long, output.schema, research.synthesize, structured_output, tools, tools.call, tools.faithful, tools.loop_ends, tools_loop_terminated
served 3.9k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.write, faithful_tool_result, lang.en, lang.hi, lang.kn, lang.te, output.long, output.schema, research.synthesize, structured_output, tools, tools.call, tools.faithful, tools.loop_ends, tools_loop_terminated
served 5.0k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.write, faithful_tool_result, lang.en, lang.kn, lang.te, output.long, output.schema, structured_output, tools, tools.call, tools.faithful, tools.loop_ends, tools_loop_terminated
served 3.5k tokens across the network
unknown publisher
held on Linux · x86-64 · no GPU · 32 GiB: embed.vector
unknown publisher
held on Linux · x86-64 · no GPU · 32 GiB: embed.vector
unknown publisher
held on Windows · x86-64 · Intel GPU · 16 GiB: embed.vector
unknown publisher
held on Linux · x86-64 · no GPU · 32 GiB: code.write, instruct.follow, lang.en, output.long, output.schema, structured_output
served 3.1k tokens across the network
unknown publisher
held on Linux · x86-64 · no GPU · 32 GiB: code.write, instruct.follow, lang.en, output.long, output.schema, structured_output
served 3.5k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.write, instruct.follow, lang.en, output.long, output.schema, structured_output
served 12.7k tokens across the network
unknown publisher
held on Linux · x86-64 · no GPU · 32 GiB: lang.hi, output.schema, structured_output
served 9.7k tokens across the network
unknown publisher
held on Linux · x86-64 · no GPU · 32 GiB: lang.bn, lang.hi, output.schema, structured_output
served 2.2k tokens across the network
unknown publisher
held on Linux · x86-64 · no GPU · 32 GiB: output.schema, structured_output
served 5.0k tokens across the network
unknown publisher
held on Linux · x86-64 · no GPU · 32 GiB: output.schema, structured_output
served 14.8k tokens across the network
unknown publisher
held on Linux · x86-64 · no GPU · 32 GiB: code.write, lang.hi, output.schema, structured_output
served 9.3k tokens across the network
unknown publisher
held on Linux · x86-64 · no GPU · 32 GiB: code.write, lang.hi, output.schema, structured_output
served 6.0k tokens across the network
unknown publisher
held on Linux · x86-64 · no GPU · 32 GiB: lang.en, output.schema, structured_output
served 8.3k tokens across the network
unknown publisher
held on Linux · x86-64 · no GPU · 32 GiB: code.reason
served 3.8k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.write, faithful_tool_result, instruct.follow, lang.en, output.schema, structured_output, tools, tools.call, tools.faithful, tools.loop_ends, tools_loop_terminated
served 223.2k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 6.4k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 29.0k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.bn, lang.en, lang.gu, lang.hi, lang.ja, lang.kn, lang.ml, lang.mr, lang.nl, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 327.8k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.loop_ends, tools.multi_hop, tools_loop_terminated, vision, vision.count, vision.multi_image, vision.read, vision.spatial
served 4.7k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.write, instruct.follow, lang.bn, lang.en, lang.hi, lang.kn, lang.ml, lang.mr, lang.pa, lang.ta, lang.te, output.long, output.schema, research.synthesize, structured_output
served 2.6k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, instruct.follow, lang.en, lang.hi, lang.mr, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.loop_ends, tools_loop_terminated
served 12.9k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.am, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.nl, lang.pa, lang.ru, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.multi_hop
served 6.9k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.multi_hop
served 5.0k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, faithful_tool_result, instruct.follow, lang.bn, lang.en, lang.gu, lang.hi, lang.kn, lang.ml, lang.mr, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.multi_hop
served 5.2k tokens across the network
unknown publisher
unknown publisher
held on Linux · x86-64 · no GPU · 32 GiB: code.write, faithful_tool_result, instruct.follow, lang.en, lang.hi, lang.kn, lang.te, output.long, output.schema, structured_output, tools, tools.call, tools.faithful, tools.loop_ends, tools_loop_terminated
served 109.7k tokens across the network
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, faithful_tool_result, lang.en, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.multi_hop
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, faithful_tool_result, lang.bn, lang.en, lang.hi, lang.ml, lang.pa, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.multi_hop
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, faithful_tool_result, lang.en, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.multi_hop
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, faithful_tool_result, lang.bn, lang.en, lang.ta, lang.te, output.long, output.schema, reason.channel, research.synthesize, structured_output, thinking, tools, tools.call, tools.faithful, tools.multi_hop
unknown publisher
held on Linux · x86-64 · NVIDIA · 32 GiB: code.reason, code.write, instruct.follow, lang.bn, lang.en, lang.hi, lang.mr, lang.ta, lang.te, output.long, output.schema, research.synthesize, structured_output
unknown publisher
Every number is a signed measurement or a count of them. grams is how many distinct nodes contributed: a verified floor, not a complete account. Lineage (publisher, attribution, base, cohort, rung) is from the catalog and is not a measurement.
grams and classes are what THIS window heard from; coverage, refusals, cost and demand carry across windows, because a gram going to sleep does not unmake what it measured.