community pool / model answer

Qwen3-4B

chat · Qwen/Qwen3-4B

55.3 tok/s · model median · 15 runs in the model record.

Reference rig	Quantization	Median result	Basis	TTFT (ms)	Peak VRAM	Max context	Engines
Arc Pro B60 24GB	4-bit	76 tok/s	reported	265	- GB	2,048	llama.cpp
Arc Pro B70 32GB	4-bit	100.5 tok/s	reported	184	- GB	2,048	llama.cpp
AMD Ryzen 7 7840HS	4-bit	22.3 tok/s	reported	-	- GB	512	llama.cpp
RX 570 4GB ×2	4-bit	54.9 tok/s	measured	78	- 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.