community pool / model answer
DeepSeek-R1-Distill-Qwen-14B-GGUF
chat · bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF
31.5 tok/s · model median · 20 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3060 12GB ×2 | 4-bit | 28.3 tok/s | measured | 5,295 | 16.5 GB | 131,072 | llama.cpp |
| RTX 3090 24GB | 4-bit | 43 tok/s | measured | 4,800 | - GB | 131,072 | llama.cpp |
| Ryzen AI Max 395 64GB | 4-bit | 24 tok/s | reported | 1,919 | 10 GB | 8,192 | 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.