Gram ·dae679 is P13 of 19 on the 50GRAMx provider standings with 6 points, from 3 signed runs on 1 machine in Singapore. Their fastest signed result is Gemma 4 E2B at 95 tokens per second. They hold the network's best result on 1 build and were the first machine anywhere to measure 0. 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/dae679)
Activity
6 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
Card (fp16 TFLOP/s)beats 80%
Memory bandwidthbeats 57%
CPU, all coresbeats 65%
CPU, one corebeats 57%
Disk readbeats 74%
Questions
What machine does Gram ·dae679 run?
Linux · NVIDIA L4 22 GB · 12 CPUs · 53 GB RAM. Every part is benchmarked and signed by the machine itself.
How many AI benchmarks has Gram ·dae679 signed?
3 signed runs across 3 builds; 1 in the last 30 days.
What is Gram ·dae679's fastest model?
Gemma 4 E2B (4-bit by unsloth) at 95 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 ·dae679 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.
2 modelsclick a column to sort by it · click a model for every machine it ran on
Gemma 4 E2B95 tok/s4-bit by unsloth
NVIDIA L4
