community pool / model answer
Qwen2.5-Coder-7B-Instruct
code · Qwen/Qwen2.5-Coder-7B-Instruct
112.5 tok/s · model median · 6 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 2080 8GB | 4-bit | 93 tok/s | reported | - | 4.7 GB | 2,048 | ollama |
| RTX 3060 12GB | 4-bit | 119 tok/s | reported | - | 4.7 GB | 2,048 | ollama |
| RTX 3080 12GB | 4-bit | 140.8 tok/s | measured | - | 8.2 GB | 2,048 | llama.cpp, ollama |
| RTX3060+RTX2080-pooled-20GB 20GB | 4-bit | 106 tok/s | reported | - | 4.7 GB | 2,048 | ollama |
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.