P8 of 36 ▲28 · 259 pts · +12949 this week
last signed within the hourclaimedBengaluru North, Karnataka1 machineearliest result held 2026-10-28
Points
259
443 behind P1
Signed runs
68
44 in 30 days
Builds measured
68
Best results held
17
3 pts each
Firsts
14
10 pts each
Rooms
0
Carbon per M tokens
737 g
median · modelled · India grid average
Gram ·9e3c79 is P8 of 36 on the 50GRAMx provider standings with 259 points, from 68 signed runs on 1 machine in Bengaluru North, Karnataka. Their fastest signed result is Gemma 3 270M at 52 tokens per second. They hold the network's best result on 17 builds and were the first machine anywhere to measure 14. Every number is signed by the machine that measured it.
Fastest models on their machines
Output tokens per second, signed · higher is better
Gemma 3 270M52 tok/s4-bit by unsloth
Qwen2.5 0.5B Instruct28 tok/s4-bit by Qwen
MiniCPM5 1B22 tok/s4-bit by openbmb
Llama 3.2 1B18 tok/s3-bit by maziyarpanahiGemma 4 E2B13 tok/s3-bit by unsloth
Hunyuan MT 2 1.8B12 tok/s4-bit by tencent
Phi 4 Mini-Reasoning10 tok/s2-bit by unsloth
Sarvam-18 tok/s4-bit by bartowskiLlama 3.2 3B7 tok/s4-bit by unslothQwen 3 4B5 tok/s3-bit by unslothA million tokens here
Metered on their machine · OpenRouter price beside it where one is sold
Gemma 3 270M$1.38no API sells itQwen2.5 0.5B Instruct$2.58no API sells itMiniCPM5 1B$3.29no API sells itLlama 3.2 1B$4.01OpenRouter $0.20Gemma 4 E2B$5.60no API sells itHunyuan MT 2 1.8B$5.82OpenRouter $0.18Phi 4 Mini-Reasoning$7.31no API sells itSarvam-1$8.83no API sells itLlama 3.2 3B$9.92OpenRouter $0.33Qwen 3 4B$16no API sells itWhat they measured, by family
Signed runs per model family
Every part as the gram benchmarked and signed it.
Intel(R) UHD Graphics 730
2 GB VRAM
CPU
12th Gen Intel Core i3-12100
8554 hashes/s all cores
Memory
15.7 GB
5.2 GB/s · 16.3 ns latency
Disk
disk
3160 MB/s read · 664 MB/s write · 164226 IOPS
Network
4.3 MiB/s download
Where
Bengaluru North, Karnataka
Against every machine on the network
Windows · Intel(R) UHD Graphics 730 2 GB · 8 CPUs · 16 GB RAM. Every part is benchmarked and signed by the machine itself.
68 signed runs across 68 builds; 44 in the last 30 days.
Gemma 3 270M (4-bit by unsloth) at 52 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 | 13Intel 2 GB | 128k | 10 + 20 lang | $5.60metered | not sold | Anyone | only on this network |
Text & chat · by Qwen8 builds | 4B | 2.3 GB | 4.6Intel 2 GB | 64k | 8 + 5 lang | $16metered | not sold | Anyone | only on this network |
Text & chat · by openbmb1 build | 1B | 0.6 GB | 22Intel 2 GB | 64k | 7 + 1 lang | $3.29metered | not sold | Anyone | only on this network |
Text & chat · by meta-llama17 builds · 2 variants | 3.2B | 1.9 GB | 7.3Intel(R) UHD Graphics 730 2 GB | 128k | 6 + 9 lang | $9.92metered | $0.332 providers | Anyone | API 30× cheaper |
Text & chat · by microsoft10 builds | ≈4.1B | 2.3 GB | 9.88 CPUs, no GPU | 4k | 5 + 3 lang | $7.31metered | not sold | Anyone | only on this network |
Text & chat · by meta-llama11 builds | 1.2B | 0.8 GB | 188 CPUs, no GPU | 32k | 5 + 8 lang | $4.01metered | $0.201 provider | Anyone | API 20× cheaper |
Text & chat · by google7 builds | 270M | 0.2 GB | 52Intel 2 GB | 32k | 4 + 3 lang | $1.38metered | not sold | Anyone | only on this network |
Text & chat · by Qwen3 builds | 500M | 0.5 GB | 28Intel(R) UHD Graphics 730 2 GB | 32k | 4 + 5 lang | $2.58metered | not sold | Anyone | only on this network |
Text & chat · by microsoft21 builds | ≈4.1B | 2.3 GB | 4.48 CPUs, no GPU | 128k | 4 + 7 lang | $16metered | not sold | Anyone | only on this network |
Text & chat · by sarvamai2 builds | 2B | 1.4 GB | 8.2Intel(R) UHD Graphics 730 2 GB | 8k | 2 + 9 lang | $8.83metered | 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 SWivid1 build | 150M | 0.6 GB | ran, not timed | — | 1 | — | not sold | Own machines only | only on this network |
Text to speech · by hexgrad1 build | — | 0.3 GB | ran, not timed | — | 1 + 1 lang | — | not sold | Not checked | only on this network |
Speech to text · by UsefulSensors1 build | — | 0.1 GB | ran, not timed | — | 1 + 1 lang | — | not sold | Anyone | 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 |
Other · by rhasspy1 build | — | — | ran, not timed | — | 1 + 1 lang | — | not sold | Not checked | 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 |
 Image generation · by segmind1 build | 320M | 1 GB | ran, not timed | — | 1 | — | not sold | Anyone | only on this network |
 Speech to text · by openai1 build | 770M | 2.8 GB | ran, not timed | — | 1 + 4 lang | — | not sold | Anyone | only on this network |
Speech to text · by openai1 build | 240M | 0.9 GB | ran, not timed | — | 1 + 6 lang | — | not sold | Anyone | only on this network |
Text & chat · by tencent4 builds | 1.8B | 0.9 GB | 12Intel(R) UHD Graphics 730 2 GB | — | — | $5.82metered | $0.181 provider | Anyone | API 33× 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 |
 Other · by lightricks1 build | 13B | — | ran, not timed | — | — | — | not sold | Not checked | 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 harahan1 build | 2B | — | ran, not timed | — | — | — | not sold | Not checked | only on this network |
Other · by languaman1 build | — | — | ran, not timed | — | — | — | not sold | Not checked | only on this network |
Other · by aemotionstudio1 build | — | — | ran, not timed | — | — | — | not sold | Not checked | 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 |
