P7 of 16 · 203 pts · +144 this week
last signed 14 h agonot claimed yetThe Dalles, Oregon1 machineearliest result held 2026-10-28
Points
203
411 behind P1
Signed runs
40
14 in 30 days
Builds measured
40
Best results held
11
3 pts each
Firsts
13
10 pts each
Rooms
0
Gram ·e3654f is P7 of 16 on the 50GRAMx provider standings with 203 points, from 40 signed runs on 1 machine in The Dalles, Oregon. Their fastest signed result is Llama 3.2 1B at 11 tokens per second. They hold the network's best result on 11 builds and were the first machine anywhere to measure 13. Every number is signed by the machine that measured it.
Fastest models on their machines
Output tokens per second, signed · higher is better
Llama 3.2 1B11 tok/s
gpt-oss 20B4 tok/s4-bit by unsloth
Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUF4 tok/s6-bit by huihui-ai
Hunyuan MT 2 30B-A3B4 tok/s4-bit by tencent
gpt-oss-20b-Derestricted3 tok/s5-bit by MaziyarPanahiHuihui-gpt-oss-20b-BF16-abliterated3 tok/s8-bit by DavidAU
Kimi Linear 48B-A3B3 tok/s4-bit by bartowski
GLM-4.7 Flash2 tok/s4-bit by unsloth
North 1.0 Mini-Code-1-02 tok/s4-bit by unsloth
Muse Glimmer 30B1 tok/s4-bit by meta-modelsA million tokens here
Metered on their machine · OpenRouter price beside it where one is sold
Llama 3.2 1B$2.66OpenRouter $0.20gpt-oss 20B$8.95OpenRouter $0.09Hunyuan MT 2 30B-A3B$12OpenRouter $0.29gpt-oss-20b-Derestricted$13no API sells itHuihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUF$13OpenRouter $0.90Huihui-gpt-oss-20b-BF16-abliterated$15no API sells itGLM-4.7 Flash$18OpenRouter $0.40Kimi Linear 48B-A3B$18no API sells itNorth 1.0 Mini-Code-1-0$20no API sells itWhat they measured, by family
Signed runs per model family
Every part as the gram benchmarked and signed it.
CPU only
linux · x86_64
CPU
Intel Xeon @ 2.2 GHz
2 cores / 4 threads · 55 MB L3 · 438 hashes/s all cores
Memory
31.3 GB
2.5 GB/s · 72.3 ns latency
Disk
overlayfs
3736 MB/s read · 191 MB/s write · 414189 IOPS
Where
The Dalles, Oregon
Uptime history starts once the bootstrap runs the build that keeps it (epnd 4317fc1).
Against every machine on the network
Linux · no GPU · 4 CPUs · 31 GB RAM. Every part is benchmarked and signed by the machine itself.
40 signed runs across 40 builds; 14 in the last 30 days.
Llama 3.2 1B at 11 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 openai3 builds · 2 variants | 20B | 10.8 GB | 4.44 CPUs, no GPU· Kaggle | 4k | 7 + 9 lang | $8.95metered | $0.0911 providers | Anyone | API 99× cheaper |
Text & chat · by moonshotai1 build | 48B3B active | 28 GB | 2.94 CPUs, no GPU | 4k | 7 + 9 lang | $18metered | not sold | Anyone | only on this network |
Text & chat · by zai-org3 builds · 1 variant | ≈28B | 15.7 GB | 2.54 CPUs, no GPU | 4k | 7 + 8 lang | $18metered | $0.402 providers | Anyone | API 45× cheaper |
Text & chat · by CohereLabs4 builds | ≈31B | 17.2 GB | 2.24 CPUs, no GPU | 4k | 7 + 9 lang | $20metered | not sold | Anyone | only on this network |
Text & chat · by meta-llama11 builds | 1.2B | 0.8 GB | 114 CPUs, no GPU | 32k | 5 + 8 lang | $2.66metered | $0.201 provider | Anyone | API 13× cheaper |
Text & chat · by tencent2 builds · 1 variant | 30B3B active | 17 GB | 3.64 CPUs, no GPU | 4k | 5 + 10 lang | $12metered | $0.291 provider | Anyone | API 41× cheaper |
 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 |
 Text to speech · by facebook1 build | 40M | 0.1 GB | ran, not timed | — | 1 | — | not sold | Own machines only | 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 |
Text to speech · by facebook1 build | 40M | 0.1 GB | ran, not timed | — | 1 | — | not sold | Own machines only | 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 |
Text to speech · by facebook1 build | 40M | 0.1 GB | ran, not timed | — | 1 | — | not sold | Own machines only | 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 |
Text to speech · by facebook1 build | 40M | 0.1 GB | ran, not timed | — | 1 | — | not sold | Own machines only | 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 |
Text to speech · by facebook1 build | 40M | 0.1 GB | ran, not timed | — | 1 | — | not sold | Own machines only | 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 |
Text to speech · by facebook1 build | 40M | 0.1 GB | ran, not timed | — | 1 | — | not sold | Own machines only | 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 |
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 |
 Speaker recognition · by speechbrain1 build | 20M | 0.1 GB | ran, not timed | — | 1 | — | 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 |
Speech to text · by vasista221 build | 240M | 0.9 GB | ran, not timed | — | 1 + 1 lang | — | not sold | Anyone | only on this network |
Speech to text · by vasista221 build | 240M | 0.9 GB | ran, not timed | — | 1 + 1 lang | — | not sold | Anyone | only on this network |
Speech to text · by vasista221 build | 240M | 0.9 GB | ran, not timed | — | 1 + 1 lang | — | not sold | Anyone | only on this network |
Text & chat · by meta-models5 builds · 1 variant | 30B | 15.6 GB | 1.3machine not reported | — | — | — | $1.202 providers | Anyone | measured |
 Text & chat · by Qwen3 builds | 27B | 15 GB | 0.8machine not reported | — | — | — | $2.707 providers | Anyone | measured |
 Translation · by google1 build | 3B | 11 GB | ran, not timed | — | 0 + 10 lang | — | 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 |
Translation · by sarvamai1 build | 4B | 8 GB | ran, not timed | — | 0 + 12 lang | — | $0.102 providers | Anyone | measured |
