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 1 of 45.- DeepSeek-V4.1-Flash-1017RTX PRO 6000 Blackwell Server Edition 768GB ×8 · vllm 0.32.0 · MXFP4+FP88 contexts × 8 concurrency levels
- Peak decode
- 4,156.3 tok/s
- Peak prefill
- 15.9K tok/s
- DeepSeek-V4.1-Flash-1017RTX PRO 6000 Blackwell Server Edition 384GB ×4 · vllm 0.32.0 · MXFP4+FP88 contexts × 8 concurrency levels
- Peak decode
- 3,724.7 tok/s
- Peak prefill
- 17.9K tok/s
- DeepSeek-V4.1-Flash-1017RTX PRO 6000 Blackwell Server Edition 384GB ×4 · vllm 0.32.0 · MXFP4+FP82 contexts × 3 concurrency levels
- Peak decode
- 1,838.4 tok/s
- Peak prefill
- —
- DeepSeek-V4.1-Flash-1017RTX PRO 6000 Blackwell Server Edition 768GB ×8 · vllm 0.32.0 · MXFP4+FP82 contexts × 3 concurrency levels
- Peak decode
- 1,929.4 tok/s
- Peak prefill
- —
- Peak decode
- 311.1 tok/s
- Peak prefill
- 3,234 tok/s
- Peak decode
- 1,393.6 tok/s
- Peak prefill
- 6,607 tok/s
- Apex-35B-V1.0CMP 170HX 64GB ×2 · vllm 0.32.0rc1.dev249+g18305948a · BF166 contexts × 8 concurrency levels
- Peak decode
- 2,901.5 tok/s
- Peak prefill
- 11.7K tok/s
- Peak decode
- 200.7 tok/s
- Peak prefill
- 3,110 tok/s
- Qwen3.5-122B-A10B-AWQ-4bitCMP 170HX 64GB ×2 · vllm 0.32.0rc1.dev249+g18305948a · AWQ 4-bit6 contexts × 8 concurrency levels
- Peak decode
- 1,613.3 tok/s
- Peak prefill
- 5,659 tok/s
- Qwen3.5-122B-A10B-NVFP4CMP 170HX 64GB ×2 · vllm 0.32.0rc1.dev249+g18305948a · NVFP46 contexts × 8 concurrency levels
- Peak decode
- 1,066.4 tok/s
- Peak prefill
- 4,420 tok/s
- Peak decode
- 1,687.2 tok/s
- Peak prefill
- 5,941 tok/s
- Peak decode
- 1,788.6 tok/s
- Peak prefill
- 6,692 tok/s
- Peak decode
- 345.3 tok/s
- Peak prefill
- 1,593 tok/s
- Peak decode
- 3,107.6 tok/s
- Peak prefill
- 5,489 tok/s
- Peak decode
- 3,300.3 tok/s
- Peak prefill
- 6,111 tok/s
- Peak decode
- 775.5 tok/s
- Peak prefill
- 1,473 tok/s
- Peak decode
- 2,087.6 tok/s
- Peak prefill
- 6,266 tok/s
- Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTPCMP 170HX 64GB · vllm 0.32.0rc1.dev249+g18305948a · NVFP46 contexts × 8 concurrency levels
- Peak decode
- 807.4 tok/s
- Peak prefill
- 1,910 tok/s
- Peak decode
- 2,140.9 tok/s
- Peak prefill
- 7,108 tok/s
- Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTPCMP 170HX 64GB · vllm 0.32.0rc1.dev249+g18305948a · NVFP46 contexts × 8 concurrency levels
- Peak decode
- 791.5 tok/s
- Peak prefill
- 1,944 tok/s
- Muse-Glimmer-30B-NVFP4-W4A4CMP 170HX 64GB · vllm 0.32.0rc1.dev249+g18305948a · NVFP4 W4A45 contexts × 8 concurrency levels
- Peak decode
- 1,320.9 tok/s
- Peak prefill
- 1,954 tok/s
- Thomson-1.0-Small-NVFP4CMP 170HX 64GB · vllm 0.32.0rc1.dev249+g18305948a · NVFP46 contexts × 8 concurrency levels
- Peak decode
- 3,224.7 tok/s
- Peak prefill
- 7,178 tok/s
- Qwen3.6-27B-AWQCMP 170HX 64GB · vllm 0.32.0rc1.dev249+g18305948a · AWQ W4 g1286 contexts × 8 concurrency levels
- Peak decode
- 964.3 tok/s
- Peak prefill
- 1,921 tok/s
- Qwen3.6-27B-AWQCMP 170HX 64GB · vllm 0.32.0rc1.dev249+g18305948a · AWQ W4 g1286 contexts × 8 concurrency levels
- Peak decode
- 1,161.1 tok/s
- Peak prefill
- 1,959 tok/s
- Qwen3.5-9B-AWQ-4bitCMP 170HX 64GB · vllm 0.32.0rc1.dev249+g18305948a · W4A16 g326 contexts × 8 concurrency levels
- Peak decode
- 2,713.1 tok/s
- Peak prefill
- 5,983 tok/s