Matrix runs
A matrix run measures prompt reading (prefill) and generation (decode) speed in one go, across several context lengths and numbers of simultaneous requests. Run one with lmx speed-test matrix run.
All runs 1,102
Newest first. Page 45 of 45.- Laguna-XS-2.1-FP8H200 NVL 141GB · sglang 0.5.6.post3.dev9269+g834400705 · FP86 contexts × 8 concurrency levels
- Peak decode
- 2,867.5 tok/s
- Peak prefill
- 39.4K tok/s
- gemma-4-31B-itH200 NVL 141GB · sglang 0.5.6.post3.dev5791+gf7d4e44d8 · BF168 contexts × 8 concurrency levels
- Peak decode
- 175.0 tok/s
- Peak prefill
- 4,765 tok/s