community pool / model answer

Qwen3-0.6B

chat · Qwen/Qwen3-0.6B

141.7 tok/s · model median · 23 runs in the model record.

Reference rig	Quantization	Median result	Basis	TTFT (ms)	Peak VRAM	Max context	Engines
AMD Ryzen 7 7840HS	2-bit	152.5 tok/s	reported	-	- GB	2,048	llama.cpp
AMD Ryzen 7 7840HS	4-bit	121.1 tok/s	reported	-	- GB	2,048	llama.cpp
AMD Ryzen 7 7840HS	8-bit	81.5 tok/s	reported	-	- GB	2,048	llama.cpp
M4 Pro 24GB	16-bit	61 tok/s	reported	-	1.4 GB	2,048	llama.cpp
RTX 3060 12GB	8-bit	310.4 tok/s	reported	304	2.8 GB	4,608	llama.cpp
RTX 3060 Ti 8GB	4-bit	141.7 tok/s	measured	54	5.2 GB	131,072	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.