24 GB · 111 reports

L4 · 24 GB

Qualified results first; original reports and full tables stay below.

Text generation · Qualified results

Speeds compare only within one exact test. Recipe availability is checked on each report against the published recipe executor.

No qualified results yet · Text generation · L4 · 24 GB

6 original reports are kept as evidence but do not qualify for comparison; each report states why. This does not show that the model or GPU cannot run it.

Check model launch support View original reports Measured alternatives for this task Test your own GPU

Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

Original reports

Every report for this task, including quality, diagnostic and legacy runs that do not enter comparisons.

Original reports · 6 rows
Model	Test task	Format	Engine	Workload	Protocol	Quality score	Test date
Ministral-3-14B-Instruct-2512 ↗	Text generation	FP8	vllm	8192in-512out	wbench-fixed-http-v1	—	10/18/2026, 4:30:05 PM
Ministral-3-14B-Instruct-2512 ↗	Text generation	FP8	vllm	2048in-512out	wbench-fixed-http-v1	—	10/18/2026, 4:25:16 PM
Ministral-3-14B-Instruct-2512 ↗	Text generation	FP8	vllm	512in-512out	wbench-fixed-http-v1	—	10/18/2026, 4:20:53 PM
Ministral-3-14B-Instruct-2512-FP8 ↗	Text generation	FP8	vllm	8192in-512out	wbench-fixed-http-v1	—	10/18/2026, 4:17:56 PM
Ministral-3-14B-Instruct-2512-FP8 ↗	Text generation	FP8	vllm	2048in-512out	wbench-fixed-http-v1	—	10/18/2026, 4:13:13 PM
Ministral-3-14B-Instruct-2512-FP8 ↗	Text generation	FP8	vllm	512in-512out	wbench-fixed-http-v1	—	10/18/2026, 4:08:50 PM

Running benchmarks

0Updates automatically

No benchmarks are currently reported as running.

L4 · 24 GB · 91 queued · 0 running · 0 awaiting reassignment · 22 succeeded · 7 failed or exhausted

Methodology

Average of error-free runs for the selected recorded configuration. Missing methods and fallback runs are not ranked. Performance index = average / fastest matching hardware × 100. Value index = performance per purchase cost / best comparable value × 100. Quality is separate by dataset and protocol. Prices are dated seller listings, not completed transactions or market averages.

Updated 11/5/2026, 11:05:29 PM