Qwen3 30B-A3B Instruct

30B-A3B

Alibaba Qwen3

Qwen3 MoE with only 3B active params. Q4 ~19GB file; outperforms QwQ-32B on 16GB cards.

⬇ 11.6K HF downloads♥ 72 likesQwen/Qwen3-30B-A3B-GGUF· stats from 6/25/2026
Consumer GPUMac / Apple Silicon

41K

Max Context

3

Quant Variants

GGUF Q5_K_M

Best Quality

98.9%

Accuracy Retained

Calculate VRAMHugging FaceCompare

Quantization Variants

Per-quant VRAM, quality loss, and inference speed on RTX 4090

FormatLevelBPWVRAMPPL LossSpeedActions
GGUFQ4_K_M4.8519.0 GB2.4%95 tok/s
CalcHF
GGUFQ5_K_M5.6822.0 GB1.1%82 tok/s
CalcHF
AWQINT4417.5 GB3.4%118 tok/s
CalcHF

Similar models

Compare with Qwen3 32B
32B

Qwen3 32B Instruct

Alibaba Qwen3

Consumer GPUPro GPU
16.8 GBmin VRAM·97.5%accuracy

Qwen3 dense 32B — successor to Qwen2.5-32B with stronger reasoning and thinking mode.

8B

Qwen3 8B Instruct

Alibaba Qwen3

Consumer GPUMac / Apple Silicon
5.1 GBmin VRAM·99.4%accuracy

Latest Qwen3 dense 8B with thinking mode. Strong upgrade from Qwen2.5 7B for local deploy.

14B

Qwen3 14B Instruct

Alibaba Qwen3

Consumer GPUMac / Apple Silicon
9.5 GBmin VRAM·98.8%accuracy

Qwen3 14B — best balance of reasoning and VRAM in the 2026 Qwen lineup.

235B-A22B

Qwen3 235B-A22B Instruct

Alibaba Qwen3

Pro GPU
115.0 GBmin VRAM·97.8%accuracy

Qwen3 flagship MoE (22B active / 235B total). Q4_K_M ~142GB; rivals DeepSeek-R1 class models.