Qwen

Qwen

Qwen/Qwen3-4B

Quantizations

Quant	Quantized by	Size	Decode	Prefill	Score	Actions
q4_k_m	Unsloth Unsloth	2.3 GB	64.0 tok/s	1,754.9 tok/s	Runs well	Run

Device Comparison

Results include trials with 4,096 input tokens and 1,024 output tokens only.