community pool / model answer

MiniCPM3-4B

chat · openbmb/MiniCPM3-4B

29.4 tok/s · model median · 3 runs in the model record.

Reference rig	Quantization	Median result	Basis	TTFT (ms)	Peak VRAM	Max context	Engines
GTX 1060 3GB	4-bit	6.1 tok/s	reported	50,843	- GB	2,048	llama.cpp
RX 570 4GB	4-bit	29.4 tok/s	reported	68	- GB	2,048	llama.cpp
RX 570 4GB ×2	4-bit	35.6 tok/s	reported	33	- 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.