Qwen2.5-Coder 32B Instruct

32B

Alibaba Qwen2.5

Top-tier open coding model. HumanEval competitive with GPT-4o on 32B scale.

⬇ 104.6K HF downloads♥ 119 likesbartowski/Qwen2.5-Coder-32B-Instruct-GGUF· stats from 8/8/2026
Consumer GPUPro GPU

131K

Max Context

3

Quant Variants

GGUF Q4_K_M

Best Quality

97.5%

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_M4.8522.0 GB2.5%44 tok/sEstimated
CalcHF
EXL23.5bpw3.516.4 GB4.5%65 tok/sEstimated
CalcHF
AWQINT4419.5 GB3.5%52 tok/sEstimated
CalcHF

Similar models

Compare with Qwen2.5 32B
32B

Qwen2.5 32B Instruct

Alibaba Qwen2.5

Consumer GPUPro GPU
16.4 GBmin VRAM·97.3%accuracy

Near-GPT-4 reasoning on a 24GB VRAM card (Q4_K_S). Groundbreaking value.

7B

Qwen2.5 7B Instruct

Alibaba Qwen2.5

Consumer GPUMac / Apple Silicon
4.8 GBmin VRAM·99.3%accuracy

Alibaba's highly optimized 7B. Punches well above its weight, especially in coding.

14B

Qwen2.5 14B Instruct

Alibaba Qwen2.5

Consumer GPUMac / Apple Silicon
9.2 GBmin VRAM·98.6%accuracy

The sweet spot between performance and resource usage. 16GB VRAM with Q4.

7B

Qwen2.5-Coder 7B Instruct

Alibaba Qwen2.5

Consumer GPUMac / Apple Silicon
4.8 GBmin VRAM·98.0%accuracy

Best 7B coding model. Ideal for local dev assistants on 8–16GB VRAM.