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 25 / 40

Qwen3-14B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-14B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 11:58:25View report ↗
Qwen3-14B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-14B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 11:43:46View report ↗
Qwen3-14B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-14B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 11:32:13View report ↗
Qwen3-14B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-14B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 11:24:10View report ↗
Qwen3-VL-8B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 11:06:07View report ↗
Qwen3-VL-8B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 10:55:04View report ↗
Qwen3-VL-8B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 10:45:38View report ↗
Qwen3-VL-8B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 10:38:33View report ↗
Qwen3-8B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-8B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 10:01:31View report ↗
Qwen3-8B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-8B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 09:45:07View report ↗
Qwen3-8B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-8B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 09:35:21View report ↗
Qwen3-8B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-8B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 09:27:35View report ↗
Qwen3-4B-Instruct-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-Instruct-2507-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 09:03:58View report ↗
Qwen3-4B-Instruct-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-Instruct-2507-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 08:50:14View report ↗
Qwen3-4B-Instruct-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-Instruct-2507-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 08:42:16View report ↗
Qwen3-4B-Instruct-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-Instruct-2507-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 08:35:09View report ↗
Qwen3-4B-Thinking-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-Thinking-2507-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 08:07:12View report ↗
Qwen3-4B-Thinking-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-Thinking-2507-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 07:53:24View report ↗
Qwen3-4B-Thinking-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-Thinking-2507-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 07:44:54View report ↗
Qwen3-4B-Thinking-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-Thinking-2507-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 07:36:56View report ↗
Qwen3-VL-4B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-4B-Instruct-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 07:16:41View report ↗
Qwen3-VL-4B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-4B-Instruct-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 07:03:19View report ↗
Qwen3-VL-4B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-4B-Instruct-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 06:54:55View report ↗
Qwen3-VL-4B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-4B-Instruct-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 06:47:03View report ↗
Qwen3-4B-FP8
/root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-FP8
RTX 4090D · 48 GB
Text generation · FP8 · vLLM
2026-01-26 06:13:24View report ↗

Updated 2026-11-11T18:16:20.428Z