P5 of 36 ▼1 · 329 pts
last signed 7 days agonot claimed yetThe Dalles, Oregon1 machineearliest result held 2026-10-23
Points
329
373 behind P1
Signed runs
96
32 in 30 days
Builds measured
96
Best results held
31
3 pts each
Firsts
14
10 pts each
Rooms
0
Carbon per M tokens
448 g
median · 30 sensor reads · United States grid average
Gram ·a5be46 is P5 of 36 on the 50GRAMx provider standings with 329 points, from 96 signed runs on 1 machine in The Dalles, Oregon. Their fastest signed result is Qwen2.5 0.5B Instruct at 239 tokens per second. They hold the network's best result on 31 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
Qwen2.5 0.5B Instruct239 tok/s4-bit by Qwen
Sarvam-1111 tok/s4-bit by bartowski
Llama 3.2 3B94 tok/s1-bit by unsloth
Gemma 4 E2B91 tok/s4-bit by google
Phi 4 Mini74 tok/s4-bit by unslothQwen 3 4B61 tok/s1-bit by unsloth
gpt-oss 20B55 tok/s3-bit by unsloth
GLM-4.7 Flash45 tok/s4-bit by unsloth
Airavata 7B (Hindi)32 tok/s4-bit by mradermacherOpenHathi 7B Hindi base30 tok/s4-bit by QuantFactoryA million tokens here
Metered on their machine · OpenRouter price beside it where one is sold
Qwen2.5 0.5B Instruct$0.56no API sells itSarvam-1$1.22no API sells itLlama 3.2 3B$1.43OpenRouter $0.33Gemma 4 E2B$1.54no API sells itPhi 4 Mini$1.84no API sells itQwen 3 4B$2.21no API sells itgpt-oss 20B$2.62OpenRouter $0.13Airavata 7B (Hindi)$4.36no API sells itOpenHathi 7B Hindi base$4.62no API sells itGLM-4.7 Flash$5.62OpenRouter $0.40What they measured, by family
Signed runs per model family
Every part as the gram benchmarked and signed it.
Tesla T4
24.5 TFLOP/s fp16 · 15 GB VRAM · 25.8 W
CPU
Intel Xeon @ 2 GHz
2 cores / 4 threads · 38.5 MB L3 · 388 hashes/s all cores
Memory
31.3 GB
0.7 GB/s · 114.5 ns latency
Disk
overlayfs
1931 MB/s read · 1 MB/s write · 120098 IOPS
Where
The Dalles, Oregon
Against every machine on the network
Linux · 2× Tesla T4 15 GB each · 4 CPUs · 31 GB RAM. Every part is benchmarked and signed by the machine itself.
96 signed runs across 96 builds; 32 in the last 30 days.
Qwen2.5 0.5B Instruct (4-bit by Qwen) at 239 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 | 912× Tesla T4 15 GB· Kaggle | 128k | 10 + 20 lang | $1.54metered | not sold | Anyone | only on this network |
Text & chat · by Google5 builds | 12B | 6.6 GB | ran, not timed | 256k | 10 + 14 lang | — | not sold | Anyone | only on this network |
Text & chat · by Google3 builds | 26B4B active | 15.8 GB | ran, not timed | 128k | 10 + 20 lang | — | $0.1015 providers · free tier | Anyone | measured |
Text & chat · by Google2 builds | 31B | 17.1 GB | ran, not timed | 128k | 10 + 20 lang | — | $0.4018 providers · free tier | Anyone | measured |
Text & chat · by Google8 builds | 8B4B active | 4.6 GB | ran, not timed | 128k | 10 + 14 lang | — | not sold | Anyone | only on this network |
Text & chat · by Qwen7 builds · 5 variants | 27B | 15 GB | 2.82× Tesla T4 15 GB·Kaggle | 8k | 9 + 14 lang | $94metered | $1.8823 providers | Anyone | API 50× cheaper |
Text & chat · by Qwen8 builds | 4B | 2.3 GB | 61NVIDIA 15 GB | 64k | 8 + 5 lang | $2.21metered | not sold | Anyone | only on this network |
Text & chat · by openai8 builds · 5 variants | 20B | 10.8 GB | 552× Tesla T4 15 GB·Kaggle | 128k | 8 + 18 lang | $2.62metered | $0.1311 providers | Anyone | API 20× cheaper |
Text & chat · by zai-org3 builds · 2 variants | ≈28B | 15.7 GB | 452× Tesla T4 15 GB·Kaggle | 128k | 8 + 16 lang | $5.62metered | $0.402 providers | Anyone | API 14× cheaper |
Text & chat · by Qwen5 builds | 4B | 7.5 GB | 12NVIDIA 15 GB | 128k | 8 + 9 lang | $12metered | not sold | Anyone | only on this network |
Text & chat · by yuxinlu14 builds | 12B | — | ran, not timed | 128k | 8 + 13 lang | — | not sold | Not checked | only on this network |
Text & chat · by Qwen3 builds | 14B | 8.4 GB | ran, not timed | 64k | 8 + 7 lang | — | $0.222 providers | Anyone | measured |
Text & chat · by Qwen1 build | 1.7B | — | ran, not timed | 64k | 7 + 1 lang | — | not sold | Anyone | only on this network |
Text & chat · by Qwen1 build | 8B | — | ran, not timed | 64k | 7 + 4 lang | — | not sold | Anyone | only on this network |
Text & chat · by meta-llama17 builds · 2 variants | 3.2B | 1.9 GB | 94NVIDIA 15 GB | 128k | 6 + 9 lang | $1.43metered | $0.332 providers | Anyone | API 4.3× cheaper |
Text & chat · by Qwen2 builds · 1 variant | 8B | 4.7 GB | ran, not timed | 128k | 6 + 7 lang | — | $0.751 provider | Anyone | measured |
 Text & chat · by redhatai1 build | — | — | ran, not timed | 32k | 5 + 6 lang | — | not sold | Not checked | only on this network |
Text & chat · by Qwen3 builds | 500M | 0.5 GB | 239NVIDIA 15 GB | 32k | 4 + 5 lang | $0.56metered | not sold | Anyone | only on this network |
Text & chat · by microsoft21 builds | ≈4.1B | 2.3 GB | 74NVIDIA 15 GB | 128k | 4 + 7 lang | $1.84metered | not sold | Anyone | only on this network |
Text & chat · by sarvamai1 build | 24B | 13.3 GB | 16NVIDIA 15 GB | 8k | 4 + 9 lang | $9.33metered | not sold | Anyone | only on this network |
 Text & chat · by krutrim-ai-labs1 build | 12B | 7 GB | 14NVIDIA 15 GB | 64k | 4 + 10 lang | $10metered | not sold | You & your company | only on this network |
Text & chat · by microsoft3 builds | ≈15B | 8.4 GB | ran, not timed | 32k | 4 + 9 lang | — | not sold | Anyone | only on this network |
Text & chat · by Qwen2 builds | 30B3B active | 16 GB | ran, not timed | 128k | 4 + 9 lang | — | $0.602 providers | Anyone | measured |
Text & chat · by sarvamai2 builds | 2B | 1.4 GB | 111NVIDIA 15 GB | 8k | 2 + 9 lang | $1.22metered | not sold | Not checked | only on this network |
Text & chat · by ai4bharat1 build | 7B | 3.9 GB | 32NVIDIA 15 GB | 4k | 2 + 2 lang | $4.36metered | not sold | Anyone | only on this network |
Text & chat · by sarvamai1 build | 7B | 3.9 GB | 30NVIDIA 15 GB | — | 1 | $4.62metered | not sold | Anyone | 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 | — | 0.2 GB | ran, not timed | — | 1 + 1 lang | — | not sold | Anyone | 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 | 1.5B | 11.1 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 |
 Video generation · by Wan-AI1 build | 1.3B | 26.9 GB | ran, not timed | — | 1 | — | not sold | Anyone | 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 | 810M | 1.5 GB | ran, not timed | — | 1 + 10 lang | — | not sold | Anyone | only on this network |
Image generation · by THUDM1 build | 5B | 20 GB | ran, not timed | — | — | — | not sold | You & your company | only on this network |
 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 |
 Image generation · by tencent1 build | 13B | 39 GB | ran, not timed | — | — | — | not sold | Not checked | only on this network |
 Image generation · by Lightricks1 build | 2B | 23.6 GB | ran, not timed | — | — | — | not sold | You & your company | only on this network |
Other · by lightx2v1 build | — | — | ran, not timed | — | — | — | not sold | Not checked | only on this network |
Other · by alibaba-pai1 build | 1.3B | — | 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 |
