community pool / model answer
Kimi-Linear-48B-A3B-Instruct
chat · moonshotai/Kimi-Linear-48B-A3B-Instruct
233.1 tok/s · model median · 6 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX PRO 6000 Blackwell 96GB | 5-bit | 267 tok/s | reported | 75 | - GB | 262,144 | llama.cpp |
| RTX PRO 6000 Blackwell 96GB | 6-bit | 256.3 tok/s | reported | 107 | - GB | 262,144 | llama.cpp |
| RTX PRO 6000 Blackwell 96GB | 8-bit | 119 tok/s | measured | 416,256 | - GB | 1,000,000 | 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.