community pool / model answer
DeepSeek-R1-Distill-Qwen-14B
chat · deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
38 tok/s · model median · 10 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3090 24GB | 4-bit | 41 tok/s | measured | 4,800 | 0 GB | 131,072 | llama.cpp |
| RTX 5000 16GB | 4-bit | 24.4 tok/s | reported | - | 15.2 GB | 57,344 | 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.