1 build of Qwen 3 8B · mradermacher measured on real machines — different packagers, precisions and engines, each a different file with its own numbers. The best each engine proved is first; every build has its own page with the machines and signatures behind it.
proved 4K context proved by mradermacher Q2_K
22.4 tok/s peak, by mradermacher Q2_K
proved by at least one build: Tool calling · Tool loop finished · Structured output · Sustained output · Vision · Counts in images · Spatial reasoning · Writes code · Follows instructions
| build | publisher | precision | engine | whose work | context proved | best tok/s | machines |
|---|---|---|---|---|---|---|---|
| hf.co/mradermacher/Qwen3-VL-8B-Instruct-abliterated-GGUF:Q2_Ksafety removed | mradermacher | Q2_K | ollama | derivative | 4,096 | 22.4 | 3 |