community pool / model answer

gemma-4-12B-coder-fable5-composer2.5-v1-GGUF

code · yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF

38.4 tok/s · model median · 2 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 5090 32GB8-bit85.3 tok/sreported112- GB2,048lmstudio
Ryzen AI Max 395 128GB4-bit24.8 tok/sreported2189.4 GB4,096llama.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.