community pool / model answer

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

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

51.4 tok/s · model median · 10 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 5070 12GB4-bit261.4 tok/sreported68- GB2,048llama.cpp
RX 570 4GB ×24-bit51 tok/smeasured90- 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.