community pool / model answer
Qwen3-0.6B-GGUF
chat · Qwen/Qwen3-0.6B-GGUF
117.5 tok/s · model median · 36 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3060 12GB | 4-bit | 117.5 tok/s | measured | 63 | - GB | 131,072 | llama.cpp |
| RTX 3060 12GB ×2 | 4-bit | 144.4 tok/s | measured | 518 | 6.1 GB | 131,072 | llama.cpp |
| RTX PRO 6000 Blackwell 96GB | 4-bit | 956.4 tok/s | reported | - | 1.1 GB | 640 | llama.cpp |
Context tested
The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.