Benchmark reports

Browse recorded runs. Open a report for its test conditions, results and eligibility for comparison.

Advanced explorer Image generation Compare measured configurations

Search reportsTaskHardware

More filters

FormatEngine

Reset filters

999 reports · Newest first · Page 27 / 40

Qwen3-0.6B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-0___6B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 03:25:08View report ↗
Qwen3-0.6B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-0___6B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 03:23:28View report ↗
Qwen3-0.6B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-0___6B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 03:17:13View report ↗
Qwen3-0.6B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-0___6B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 03:14:02View report ↗
Qwen3-0.6B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-0___6B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 03:07:30View report ↗
Qwen3-0.6B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-0___6B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 03:06:33View report ↗
Qwen3-0.6B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-0___6B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 03:00:09View report ↗
Qwen3-0.6B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-0___6B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 02:57:39View report ↗
Qwen3-0.6B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-0___6B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 02:25:35View report ↗
Qwen3-0.6B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-0___6B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 01:29:36View report ↗
Qwen3-1.7B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-1___7B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-25 17:14:18View report ↗
Qwen3-1.7B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-1___7B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-25 17:01:45View report ↗
Qwen3-1.7B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-1___7B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-25 16:49:37View report ↗
Qwen3-1.7B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-1___7B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-25 16:37:27View report ↗
Qwen3-8B-AWQ
/root/.cache/modelscope/hub/models/Qwen/Qwen3-8B-AWQ
RTX 4090D · 48 GB
Text generation · AWQ · vLLM
2026-01-25 07:35:48View report ↗
Qwen3-8B-AWQ
/root/.cache/modelscope/hub/models/Qwen/Qwen3-8B-AWQ
RTX 4090D · 48 GB
Text generation · AWQ · vLLM
2026-01-25 07:20:41View report ↗
Qwen3-8B-AWQ
/root/.cache/modelscope/hub/models/Qwen/Qwen3-8B-AWQ
RTX 4090D · 48 GB
Text generation · AWQ · vLLM
2026-01-25 07:10:33View report ↗
Qwen3-8B-AWQ
/root/.cache/modelscope/hub/models/Qwen/Qwen3-8B-AWQ
RTX 4090D · 48 GB
Text generation · AWQ · vLLM
2026-01-25 07:01:23View report ↗
Qwen3-8B-AWQ
/root/.cache/modelscope/hub/models/Qwen/Qwen3-8B-AWQ
RTX 4090D · 48 GB
Text generation · AWQ · vLLM
2026-01-25 06:53:38View report ↗
Qwen3-8B-AWQ
/root/.cache/modelscope/hub/models/Qwen/Qwen3-8B-AWQ
RTX 4090D · 48 GB
Text generation · AWQ · vLLM
2026-01-25 06:45:32View report ↗
Qwen3-4B-AWQ
/root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-AWQ
RTX 4090D · 48 GB
Text generation · AWQ · vLLM
2026-01-25 06:32:49View report ↗
Qwen3-4B-AWQ
/root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-AWQ
RTX 4090D · 48 GB
Text generation · AWQ · vLLM
2026-01-25 06:24:57View report ↗
Qwen3-4B-AWQ
/root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-AWQ
RTX 4090D · 48 GB
Text generation · AWQ · vLLM
2026-01-25 06:17:50View report ↗
Qwen3-4B-AWQ
/root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-AWQ
RTX 4090D · 48 GB
Text generation · AWQ · vLLM
2026-01-25 06:10:53View report ↗
Gemma-3-270m
/root/.cache/modelscope/hub/models/google/gemma-3-270m
RTX 4090D · 48 GB
Text generation · BF16 · vLLM
2026-01-25 06:03:52View report ↗

Updated 2026-11-11T19:40:52.367Z