community pool / model answer
supergemma4-26b-uncensored-gguf-v2
chat · Jiunsong/supergemma4-26b-uncensored-gguf-v2
77.7 tok/s · model median · 2 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 5060 Ti 16GB ×2 | 4-bit | 89.4 tok/s | reported | 125 | - GB | 32,768 | llama.cpp |
| Ryzen AI Max 395 128GB | 4-bit | 66.1 tok/s | reported | - | 22.3 GB | 16,384 | 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.