community pool / model answer
Qwen2.5-7B-Instruct
chat · Qwen/Qwen2.5-7B-Instruct
53.2 tok/s · model median · 4 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| GTX 1080 Ti 11GB | 4-bit | 57.6 tok/s | reported | - | 7.4 GB | 8,192 | llama.cpp |
| GTX 1080 Ti 11GB | 5-bit | 41.1 tok/s | reported | - | 8.1 GB | 8,192 | llama.cpp |
| M1 Max 64GB | 4-bit | 48.7 tok/s | reported | 30 | - GB | 2,048 | ollama |
| RTX 4070 SUPER 12GB | 4-bit | 77.4 tok/s | reported | 248 | 7 GB | 65,536 | 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.