Gram ·662a4e is P11 of 19 on the 50GRAMx provider standings with 19 points, from 3 signed runs on 1 machine in Netherlands. Their fastest signed result is Llama 3.2 1B at 11 tokens per second. They hold the network's best result on 2 builds and were the first machine anywhere to measure 1. Every number is signed by the machine that measured it.
Fastest models on their machines
Output tokens per second, signed · higher is better
[](https://50gramx.com/inferences/providers/662a4e)
Activity
8 signed runs in the last 17 weeks, one square a day
Online 12.5% of the hours the network has a record for · last 30 days
Against every machine on the network
Memory bandwidthbeats 63%
CPU, all coresbeats 42%
CPU, one corebeats 42%
Disk readbeats 88%
Questions
What machine does Gram ·662a4e run?
Linux · no GPU · 4 CPUs · 31 GB RAM. Every part is benchmarked and signed by the machine itself.
How many AI benchmarks has Gram ·662a4e signed?
3 signed runs across 3 builds; 2 in the last 30 days.
What is Gram ·662a4e's fastest model?
Llama 3.2 1B at 11 tokens per second, signed.
How are the standings scored?
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.
Can I check these numbers myself?
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.
Every model Gram ·662a4e measured
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.
3 modelsclick a column to sort by it · click a model for every machine it ran on
Llama 3.2 1B11 tok/s
Qwen 3 VL-2B9 tok/s4-bit by Qwen
CPU only
Kaggle
