community pool / model answer
Gemma-4-26B-A4B-NVFP4
chat · nvidia/Gemma-4-26B-A4B-NVFP4
482.3 tok/s · model median · 4 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| GB10 Grace Blackwell 128GB | 4-bit | 227.5 tok/s | reported | 200 | - GB | 2,048 | vllm |
| M1 Max 64GB | 4-bit | 52.7 tok/s | reported | - | - GB | 2,048 | ollama |
| RTX PRO 6000 Blackwell Server Edition 96GB | 4-bit | 128.3 tok/s | reported | - | 87.5 GB | 65,536 | vllm |
| RTX PRO 6000 Blackwell Workstation Edition 96GB | 4-bit | 36.9 tok/s | reported | 60 | - GB | 131,072 | vllm |
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.