Qwen2.5-Coder

Qwen2.5-Coder-32B-Instruct

Alibaba (Qwen team) · open-permissive apache-2.0

Parameters (B)	32.764
Architecture	dense
Layers / KV heads / head dim	64 / 8 / 128
Context window	32768
Modalities	in: text; out: text
GGUF	available
Commercial use	yes

Minimum hardware (estimate)

At Q4_K_M and 8k context, total working set ≈ 22.6 GiB. On a machine with 64 GiB system RAM and no discrete GPU: CPU-only, slow. Limiting factor: No GPU VRAM; fits in system RAM but inference will be CPU-bound.

Open in fit advisor

Scores

Benchmark	Value	Uncertainty	Run by	Source
Aider polyglot	16.4%	unknown	third-party	epoch-ai

Provenance

identity, license, architecture, parameter count: https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct (retrieved 2026-08-10)

HF: Qwen/Qwen2.5-Coder-32B-Instruct · snapshot 2026-08-10