community pool / model answer
deepseek-v4-gguf
chat · antirez/deepseek-v4-gguf
10.8 tok/s · model median · 1 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| GB10 Grace Blackwell 128GB | 2-bit | 10.5 tok/s | reported | 5,614 | 102.3 GB | 200,000 | 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.