P7 of 36 ▲23 · 278 pts · +654 this week
last signed 2 days agoclaimedBhubaneswar, Odisha1 machineearliest result held 2026-10-28
Points
278
424 behind P1
Signed runs
53
36 in 30 days
Builds measured
53
Best results held
35
3 pts each
Firsts
12
10 pts each
Rooms
0
Carbon per M tokens
1.3 kg
median · 10 sensor reads · India grid average
Gram ·84bf54 is P7 of 36 on the 50GRAMx provider standings with 278 points, from 53 signed runs on 1 machine in Bhubaneswar, Odisha. Their fastest signed result is DeepSeek-OCR 2 Base at 412 tokens per second. They hold the network's best result on 35 builds and were the first machine anywhere to measure 12. Every number is signed by the machine that measured it.
Fastest models on their machines
Output tokens per second, signed · higher is better
DeepSeek-OCR 2 Base412 tok/s4-bit by sabafallah
MiniCPM5 1B381 tok/s4-bit by openbmb
Gemma 3 270M286 tok/s4-bit by unsloth
Qwen2.5 0.5B Instruct248 tok/s4-bit by Qwen
Llama 3.2 3B225 tok/s1-bit by unsloth
Hunyuan MT 2 1.8B222 tok/s4-bit by tencent
Phi 4 Mini205 tok/s4-bit by maziyarpanahiPhi 4 Mini-Reasoning189 tok/s3-bit by unslothGemma 4 E2B183 tok/s4-bit by unslothQwen 3 4B90 tok/s1-bit by unslothA million tokens here
Metered on their machine · OpenRouter price beside it where one is sold
DeepSeek-OCR 2 Base$0.63no API sells itMiniCPM5 1B$0.67no API sells itGemma 3 270M$0.90no API sells itQwen2.5 0.5B Instruct$1.04no API sells itLlama 3.2 3B$1.14OpenRouter $0.33Hunyuan MT 2 1.8B$1.16OpenRouter $0.18Phi 4 Mini$1.25no API sells itPhi 4 Mini-Reasoning$1.36no API sells itGemma 4 E2B$1.41no API sells itQwen 3 4B$2.84no API sells itWhat they measured, by family
Signed runs per model family
Every part as the gram benchmarked and signed it.
NVIDIA GeForce RTX 3080 Ti
59.8 TFLOP/s fp16 · 12 GB VRAM
CPU
AMD Ryzen 7 5800X 8-Core
26484 hashes/s all cores
Memory
15.9 GB
15.3 GB/s · 11.8 ns latency
Disk
disk
801 MB/s read · 74 MB/s write · 4296 IOPS
Where
Bhubaneswar, Odisha
Against every machine on the network
Windows · NVIDIA GeForce RTX 3080 Ti 12 GB · 16 CPUs · 16 GB RAM. Every part is benchmarked and signed by the machine itself.
53 signed runs across 53 builds; 36 in the last 30 days.
DeepSeek-OCR 2 Base (4-bit by sabafallah) at 412 tokens per second, signed.
1 point per signed run, 3 per build where the provider holds the network’s fastest result on that kind of machine, 10 per model they were first to measure.
Yes. Each run publishes the exact bytes the machine signed and its signature; “verify this yourself” checks it in your browser against the machine’s own key.
The seasons table, narrowed to this provider’s signed runs: speed and cost on their machines, next to what OpenRouter charges, the checks each model passed, and its licence.
| parameters | tokens/sec | proved | per M tokens | per M tokens | Verdict | ||||
|---|---|---|---|---|---|---|---|---|---|
Text & chat · by Google19 builds | 5.1B2B active | 3.8 GB | 183GeForce RTX 3080 Ti 12 GB | 128k | 10 + 20 lang | $1.41metered | not sold | Anyone | only on this network |
Text & chat · by Qwen8 builds | 4B | 2.3 GB | 90NVIDIA 12 GB | 64k | 8 + 5 lang | $2.84metered | not sold | Anyone | only on this network |
Text & chat · by openbmb1 build | 1B | 0.6 GB | 381GeForce RTX 3080 Ti 12 GB | 64k | 7 + 1 lang | $0.67metered | not sold | Anyone | only on this network |
Text & chat · by meta-llama17 builds · 2 variants | 3.2B | 1.9 GB | 225NVIDIA 12 GB | 128k | 6 + 9 lang | $1.14metered | $0.332 providers | Anyone | API 3.5× cheaper |
Text & chat · by microsoft10 builds | ≈4.1B | 2.3 GB | 189NVIDIA 12 GB | 4k | 5 + 3 lang | $1.36metered | not sold | Anyone | only on this network |
Text & chat · by google7 builds | 270M | 0.2 GB | 286GeForce RTX 3080 Ti 12 GB | 32k | 4 + 3 lang | $0.90metered | not sold | Anyone | only on this network |
Text & chat · by Qwen3 builds | 500M | 0.5 GB | 248GeForce RTX 3080 Ti 12 GB | 32k | 4 + 5 lang | $1.04metered | not sold | Anyone | only on this network |
Text & chat · by microsoft21 builds | ≈4.1B | 2.3 GB | 205GeForce RTX 3080 Ti 12 GB | 128k | 4 + 7 lang | $1.25metered | not sold | Anyone | only on this network |
Text & chat · by deepseek-ai1 build | ≈3.2B | 1.8 GB | 412GeForce RTX 3080 Ti 12 GB | — | 3 + 1 lang | $0.63metered | not sold | Anyone | only on this network |
 Text & chat · by sarvamai2 builds | 2B | 1.4 GB | 20GeForce RTX 3080 Ti 12 GB | 8k | 2 + 9 lang | $13metered | not sold | Not checked | only on this network |
Embeddings (search) · by google14 builds | 300M | 0.2 GB | ran, not timed | — | 1 | — | not sold | Anyone | only on this network |
 Text to speech · by facebook1 build | 40M | 0.1 GB | ran, not timed | — | 1 | — | not sold | Own machines only | only on this network |
Music & sound · by facebook1 build | 300M | 2.2 GB | ran, not timed | — | 1 | — | not sold | Own machines only | only on this network |
Vision (counting, locating) · by facebook1 build | 90M | 0.7 GB | ran, not timed | — | 1 | — | not sold | Anyone | only on this network |
 Image generation · by Efficient-Large-Model1 build | 1.6B | 3 GB | ran, not timed | — | 1 | — | not sold | Anyone | only on this network |
 Image generation · by stabilityai1 build | 900M | 2.4 GB | ran, not timed | — | 1 | — | not sold | Not checked | only on this network |
Speech to text · by facebook1 build | 2.3B | 8.6 GB | ran, not timed | — | 1 + 13 lang | — | not sold | Own machines only | only on this network |
 Image generation · by segmind1 build | 320M | 1 GB | ran, not timed | — | 1 | — | not sold | Anyone | only on this network |
Text & chat · by tencent4 builds | 1.8B | 0.9 GB | 222GeForce RTX 3080 Ti 12 GB | — | — | $1.16metered | $0.181 provider | Anyone | API 6.6× cheaper |
 Image generation · by THUDM2 builds | 2B | 12.8 GB | ran, not timed | — | — | — | not sold | Anyone | only on this network |
 Vision (counting, locating) · by depth-anything1 build | 100M | 0.4 GB | ran, not timed | — | — | — | not sold | Own machines only | only on this network |
Vision (counting, locating) · by depth-anything1 build | 30M | 0.1 GB | ran, not timed | — | — | — | not sold | Anyone | only on this network |
Translation · by facebook1 build | 1.3B | 5.1 GB | ran, not timed | — | 0 + 12 lang | — | not sold | Own machines only | only on this network |
Translation · by facebook1 build | 600M | 2.3 GB | ran, not timed | — | 0 + 12 lang | — | not sold | Own machines only | only on this network |
 Other · by optimum-intel-internal-testing1 build | — | — | ran, not timed | — | — | — | not sold | Not checked | only on this network |
 Other · by wan-ai1 build | 1.3B | — | ran, not timed | — | — | — | not sold | Not checked | only on this network |
