Can I run Qwen2.5 Coder 32B locally?

Yes, the weights are open and hosted on Hugging Face at Qwen/Qwen2.5-Coder-32B-Instruct. You will need a machine with enough VRAM or RAM to load a 32B model; quantized GGUF versions are available from the community for lower-memory setups.

What does it cost via API, and how long is the context?

Pricing on OpenRouter is $0.66 per million input tokens and $1.00 per million output tokens. The full context length is 131,072 tokens, though you need to enable YaRN in the config to use beyond 32,768 tokens in most local deployments.

How does the 32B compare to smaller Qwen2.5 Coder sizes?

Qwen2.5 Coder comes in six sizes from 0.5B to 32B; the 32B is the top of the range and the one the maker benchmarks against GPT-4o. Smaller sizes trade some coding capability for much lower hardware requirements.

Qwen2.5 Coder 32B Instruct

4997°

#llm #qwen #coding #agents #math #long context

Runs on Graydient

Run this model

Offers / Ads

Easy Creator (Prism) Web

Unlimited · flat fee

Best for beginners. Describe what you want in a chat and the picture comes back, no learning curve.

PirateDiffusion Telegram

Unlimited · flat fee

Images and video from a chat, with short commands. The most convenient tool for Telegram users, with a web companion.

Pro studio (SpyGlass) Web

Unlimited · flat fee

Best for power users. Full control over models, settings and workflows in a browser studio.

Discord bot (Vector)

Unlimited · flat fee

Best for communities. Add it to your own server and run any workflow from a channel.

Unified Editor Web

Unlimited · flat fee

One screen for every model and workflow: prompts, references, edits and video, built into your Graydient account.

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

Local apps

Requires setup

Set up local programs if your computer has capable hardware.

ModelDuel Web

Pay per use

Generate the same prompt on up to 50 checkpoint/base models at a time.

Rent a GPU on the cloud

Graydient Cloud GPU

Unlimited · flat fee

Flat fee, unlimited use. This model installs with one click.

RunPod Cloud GPU

Charged by the minute

Rent a GPU by the minute and set the model up yourself.

Guides for this model

Ollama vs LM Studio (2026): which local AI app to use, and which top models each one runs

How much VRAM do I actually need for local AI?

What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)

All guides

qwen | 32,768 token context | $0.66/M input, $1.00/M output. Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: To read more about its evaluation results, check out Qwen 2.5 Coder's blogOpens in new tab.

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Qwen2.5 Coder 32B Instruct is Alibaba's flagship code-specific model, trained on 5.5 trillion tokens of source code and related data. The maker claims its coding ability matches GPT-4o, which is a bold bar for an open-weights model at this price. It suits developers who want a serious coding model they can self-host or run cheaply via API.

Known for

Code generation, fixing and reasoning trained on 5.5 trillion tokens
Open weights: download and run it on your own hardware
Native context window of 131,072 tokens, extendable via YaRN
Retains strong math and general reasoning alongside coding
Available in six sizes from 0.5B to 32B for different hardware budgets

Watch out for

Default config.json caps context at 32,768 tokens; you must manually enable YaRN for longer inputs.
32B weights demand significant VRAM to run locally at full precision.
Requires transformers 4.37.0 or later or you will hit a silent KeyError at load time.

Best for

Prompts to try

Debug a broken function

Here is a Python function that is supposed to parse a CSV file and return a list of dicts, but it silently drops the last row. Find the bug, explain why it happens, and return a corrected version with a brief comment on the fix. ```python def parse_csv(path): rows = [] with open(path) as f: headers = f.readline().strip().split(',') for line in f: rows.append(dict(zip(headers, line.strip().split(',')))) return rows ```

Design a small code agent

Write a minimal Python agent loop that accepts a user goal as a string, calls a tool called run_shell(cmd) to execute bash commands, reads the output, and decides whether to call another tool or return a final answer. Include error handling for non-zero exit codes and a hard limit of ten tool calls.

Refactor for readability

Refactor the following JavaScript so it is easier to read and maintain. Do not change behaviour. Explain each change you make in a short comment above the relevant line. ```js function p(a,b,c){return a.filter(x=>x>b&&x<c).reduce((s,x)=>s+x,0)/a.filter(x=>x>b&&x<c).length||0} ```

Compare with

Qwen3.8 Max (0902)
API-only model
1,000,000 token context · $2.00/M input, $6.00/M output
Qwen3.7 Plus
API-only model
1,000,000 token context · $0.32/M input, $1.28/M output
Qwen3.6 Plus
API-only model
1,000,000 token context · $0.33/M input, $1.95/M output
Qwen3.6 Max Preview
API-only model
262,144 token context · $1.03/M input, $6.16/M output

More text models from qwen

Questions people ask

Can I run Qwen2.5 Coder 32B locally?: Yes, the weights are open and hosted on Hugging Face at Qwen/Qwen2.5-Coder-32B-Instruct. You will need a machine with enough VRAM or RAM to load a 32B model; quantized GGUF versions are available from the community for lower-memory setups.
What does it cost via API, and how long is the context?: Pricing on OpenRouter is $0.66 per million input tokens and $1.00 per million output tokens. The full context length is 131,072 tokens, though you need to enable YaRN in the config to use beyond 32,768 tokens in most local deployments.
How does the 32B compare to smaller Qwen2.5 Coder sizes?: Qwen2.5 Coder comes in six sizes from 0.5B to 32B; the 32B is the top of the range and the one the maker benchmarks against GPT-4o. Smaller sizes trade some coding capability for much lower hardware requirements.

Captain's verdict
The strongest open-weights coding model you can actually self-host, at a price that makes GPT-4o hard to justify for pure code work.

Model card on Hugging Face

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

AI Models for Image, Video & Text Generation

Qwen2.5 Coder 32B Instruct is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.

More Text / LLM models llm qwen coding agents math long context local

Browse by Model Family