Qwen3-Coder 30B-A3B Instruct

30B-A3B

Alibaba Qwen3

Agentic coding MoE with 3.3B active params and 256K native context. Top open coder for 16–24GB cards.

⬇ 1.2M HF downloads♥ 1199 likesQwen/Qwen3-Coder-30B-A3B-Instruct· stats from 8/14/2026
Consumer GPUMac / Apple Silicon

262K

Max Context

3

Quant Variants

GGUF Q5_K_M

Best Quality

99.0%

Accuracy Retained

Calculate VRAMHugging FaceCompare

Quantization Variants

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

Measured = site benchmarks · Estimated = formula · Community = public reports

FormatLevelBPWVRAMPPL LossSpeedSourceActions
GGUFQ4_K_M4.8519.2 GB2.3%92 tok/sMeasured
CalcHF
GGUFQ5_K_M5.6822.0 GB1.0%80 tok/sMeasured
CalcHF
AWQINT4417.8 GB3.2%115 tok/sMeasured
CalcHF

Similar models

Compare with Qwen3 30B-A3B
30B-A3B

Qwen3 30B-A3B Instruct

Alibaba Qwen3

Consumer GPUMac / Apple Silicon
17.5 GBmin VRAM·98.9%accuracy

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

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.

How to actually run this

Deployment guides for this model and this class of hardware.