M
Best token generation
1.593,1 tok/s
Meta-Llama-3.1-8B-Instruct
Best prefill
52.503,3 tok/s
Llama-3.2-1B-Instruct
∅ Token generation
265,9 tok/s
Average of 167 runs
∅ Prefill
8.387,2 tok/s
Average of 167 runs
Best TTFT
156 ms
Llama-3.2-1B-Instruct
Best harness rate
0%
no harness run yet
🏆
Meta-Llama-3.1-8B-Instruct · fastest model at 1.593,1 tok/s token generation
Best prefill of this manufacturer: 52.503,3 tok/s (Llama-3.2-1B-Instruct)
Best prefill of this manufacturer: 52.503,3 tok/s (Llama-3.2-1B-Instruct)
Top models by token generation
Best measured generation throughput per model (tok/s), published performance benchmarks.