community pool / model answer

Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M

chat · JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M5 Pro 24GB4-bit112.3 tok/sreported283- GB4,224llama.cpp
RTX 5070 12GB4-bit265.5 tok/sreported67- GB2,048llama.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.