community pool / model answer
DeepSeek-R1-Distill-Qwen-7B
chat · deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
63.6 tok/s · model median · 26 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 2080 8GB | 4-bit | 80 tok/s | reported | - | 4.7 GB | 2,048 | ollama |
| RTX 3060 12GB | 4-bit | 62.1 tok/s | measured | 1,247 | 4.7 GB | 131,072 | llama.cpp, ollama |
| RTX 3060 Ti 8GB | 4-bit | 67.9 tok/s | measured | 2,145 | 6.7 GB | 131,072 | llama.cpp |
| RTX 3080 12GB | 4-bit | 144 tok/s | reported | - | 4.8 GB | 2,048 | ollama |
| RTX3060+RTX2080-pooled-20GB 20GB | 4-bit | 106.5 tok/s | reported | - | 4.8 GB | 2,048 | ollama |
| RX 570 4GB ×2 | 4-bit | 23.1 tok/s | reported | 175 | - GB | 2,048 | 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.