community pool / model answer

granite-4.0-h-micro

chat · ibm-granite/granite-4.0-h-micro

45 tok/s · model median · 11 runs in the model record.

Reference rig	Quantization	Median result	Basis	TTFT (ms)	Peak VRAM	Max context	Engines
GTX 1060 3GB	4-bit	45.2 tok/s	measured	3,058	2.5 GB	2,048	llama.cpp
RX 570 4GB	4-bit	7.9 tok/s	reported	589	- GB	2,048	llama.cpp
RX 570 4GB ×2	4-bit	34.8 tok/s	measured	293	- GB	2,048	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.