What hardware do I need to run Qwen2.5-Coder 32B Instruct?

At its most compressed (Q4_K_M) it needs roughly 20GB of VRAM, and about 24GB for good quality. VRAM figures are approximate and depend on context length and settings.

Is Qwen2.5-Coder 32B Instruct free for commercial use?

Yes. Qwen2.5-Coder 32B Instruct is licensed under Apache 2.0, which permits commercial use with no meaningful conditions.

Can I run Qwen2.5-Coder 32B Instruct on Apple Silicon?

Yes. Qwen2.5-Coder 32B Instruct has builds optimised for Apple Silicon, through MLX or GGUF on a Mac.

Does Qwen2.5-Coder 32B Instruct run on CPU?

Yes, Qwen2.5-Coder 32B Instruct can run on the CPU, though generation is slower than on a GPU.

What is Qwen2.5-Coder 32B Instruct's context window?

Qwen2.5-Coder 32B Instruct has a context window of 131,072 tokens, about 131k.

Qwen2.5-Coder 32B Instruct

Name: Qwen2.5-Coder 32B Instruct
Author: Alibaba

Alibaba · Code · 32B · 131k context · Released 12 November 2024

Commercial use permitted Open weights Runs on CPU Apple Silicon

Qwen2.5-Coder 32B is the model that made a genuinely capable local coding assistant practical on one consumer card. At Q4 it fits a 24GB GPU, it is permissively licensed under Apache 2.0, and it performs strongly on the standard code benchmarks, close to much larger models at the time of release. It pairs well with editor tools like Continue, Aider, and Cline for autocomplete and agentic edits. Newer mixture-of-experts coders such as Qwen3-Coder are faster at similar memory, but the dense 32B remains a reliable, well-understood choice, and its smaller 7B sibling covers lighter hardware.

Strengths

Strong code generation and editing for a model that fits a 24GB card
Apache 2.0, so no commercial-use conditions
Long 128k context and broad tool support

Weaknesses

A dense 32B is slower than a mixture-of-experts coder at similar memory
Superseded on raw benchmarks by newer coding models
Benchmark figures below are the developer's own

Hardware requirements

Quantisation	Approx. VRAM	Notes
Q4_K_M	~20GB	Fits a 24GB card, the common way to run it locally
Q5_K_M	~23GB	Better quality, needs headroom beyond 24GB
Q8_0	~35GB	Near-lossless, needs 40GB or more
FP16	~65GB	Full precision, server or multi-GPU territory

Also runs on CPU (slower). Optimised builds available for Apple Silicon.

What you'd need to run this

Roughly what a machine to run this would need, at up to three levels of quality. Memory is the deciding factor.

Minimum to run it

Q4_K_M · ~20GB needed

One 24GB GPU

NVIDIA Tesla P40

or a Mac or mini-PC with unified memory, if you prefer no discrete GPU, Mac mini M5 Pro .

32–64GB of system RAM alongside the card.

around £700–£1,100

What else 24GB runs →

For good quality

Q5_K_M · ~23GB needed

One 32GB GPU

NVIDIA GeForce RTX 5090

or a Mac or mini-PC with unified memory, if you prefer no discrete GPU, Mac mini M4 Pro .

64GB of system RAM alongside the card.

around £4,000–£8,000

See the Single-card flagship build What else 32GB runs →

Best quality

FP16 · ~65GB needed

96GB of unified memory

AMD Ryzen AI Max+ 395 (Strix Halo)

or an 80GB-class data-centre card, which is usually rented by the hour, NVIDIA A100 80GB .

Unified memory is shared with the model, so it is already counted above.

around £1,100–£2,000

See the Quiet large-model box build What else 96GB runs →

Licence

Apache 2.0 — read the licence

Benchmarks

Benchmark	Score	Source	As of
HumanEval	92.7	Qwen2.5-Coder technical report (Table 16)	September 2024
MBPP	90.2	Qwen2.5-Coder technical report (Table 16)	September 2024
Aider (Pass@2)	73.7	Qwen2.5-Coder blog	November 2024

How it compares

How this model’s reported scores sit against other models we cover, on the same benchmarks. This model is highlighted.

MBPP

higher is better

Qwen2.5-Coder 32B Instruct 90.2

Qwen2.5-Coder technical report (Table 16) · September 2024
Qwen2.5-Coder 7B Instruct 83.5

Qwen2.5-Coder technical report · November 2024

Qwen2.5-Coder 32B Instruct: common questions

What hardware do I need to run Qwen2.5-Coder 32B Instruct?: At its most compressed (Q4_K_M) it needs roughly 20GB of VRAM, and about 24GB for good quality. VRAM figures are approximate and depend on context length and settings.
Is Qwen2.5-Coder 32B Instruct free for commercial use?: Yes. Qwen2.5-Coder 32B Instruct is licensed under Apache 2.0, which permits commercial use with no meaningful conditions.
Can I run Qwen2.5-Coder 32B Instruct on Apple Silicon?: Yes. Qwen2.5-Coder 32B Instruct has builds optimised for Apple Silicon, through MLX or GGUF on a Mac.
Does Qwen2.5-Coder 32B Instruct run on CPU?: Yes, Qwen2.5-Coder 32B Instruct can run on the CPU, though generation is slower than on a GPU.
What is Qwen2.5-Coder 32B Instruct's context window?: Qwen2.5-Coder 32B Instruct has a context window of 131,072 tokens, about 131k.

Availability

Official page
Hugging Face
ollama run qwen2.5-coder:32b

Recommended for

A strong local coding assistant on a single 24GB card
Commercial coding work needing a permissive licence
Pairing with Continue, Aider, or Cline

Related models

Run it with

Related guides

Glossary

Catalogue entry last verified 18 August 2026. Specifications change; verify anything you are about to spend money on.