community pool / model answer
gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF
chat · yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF
32.3 tok/s · model median · 6 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 4070 12GB | 4-bit | 39.7 tok/s | measured | 570 | - GB | 2,048 | vllm |
| Ryzen AI Max 395 128GB | 4-bit | 24.7 tok/s | reported | 218 | 9.4 GB | 4,096 | 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.