Qwen

Qwen2.5-Coder-32B-Instruct

SIZE33B

27Quality

Text

Downloads650K/mo

Likes2.2K

Language model from Qwen, 33B parameters.

Open weightsApache 2.0431/1044

Drag to turn

QwenTextPromo

Qwen2.5-Coder-32B-Instruct

Language model from Qwen, 33B parameters.

Qwen/Qwen2.5-Coder-32B-Instruct

Type: Text
Quality: 27 · Top 73% on the Epoch Capabilities Index
Parameters: 33B (32,763,876,352)
Downloads: 650K in the last 30 days
Likes: 2.2K
Access to weights: Open download
On Hugging Face since: Nov 6, 2024
Takes in: Text
Puts out: Text
Access: Open weights
License: Apache 2.0
Rarity: Promo
Set number: 431/1044

Open on Hugging Face Quality 27 Where to run it 10 Evolution 1/2 Race it 47 tok/s Meet its creature Battle granite-4.1-3b

License read from the model’s Hugging Face card. Stats from Qwen’s official Hugging Face account, refreshed daily.

How good is it?

Public leaderboard scores for Qwen2.5-Coder-32B-Instruct, refreshed daily from Epoch AI and LMArena.

Top 73% of the 277 models on the Epoch Capabilities Index: #202.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

Epoch Capabilities Index#202 of 277
One number fitted from dozens of hard benchmarks, from science questions to agentic coding.119.5 index
Listed as Qwen2.5-Coder-32B
LMArena Text#301 of 416
People compare two anonymous answers and vote for the better one.1,230 rating
LMArena Text · Coding#276 of 411
The text arena’s coding prompts only.1,275 rating
LMArena Text · Math#277 of 400
The text arena’s math prompts only.1,250 rating
LMArena Text · Creative writing#320 of 414
The text arena’s creative writing prompts only.1,174 rating

Scores from Epoch AI and LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

8 providers sell Qwen2.5-Coder-32B-Instruct through an API, and 2 Hugging Face hosts serve it. Prices are per million tokens, cheapest first.

CheapestNanoGPT$0.20 in · $0.20 out
Free to try1 providerNvidia
Fastest on Hugging FaceNscale47 tokens/s

API providers

Provider	Input	Output	Context
NvidiaFree`qwen/qwen2.5-coder-32b-instruct`	Free	Free	128K
NanoGPTCheapest paid`qwen/qwen2.5-coder-32b-instruct`	$0.20	$0.20	32K
Abacus`qwen-2.5-coder-32b`	$0.79	$0.79	128K
Alibaba (China)`qwen2-5-coder-32b-instruct`	$0.29	$0.86	131K
Cloudflare Workers AI`@cf/qwen/qwen2.5-coder-32b-instruct`	$0.66	$1.00	33K
Eden AI`cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct`	$0.66	$1.00	33K
Kilo Gateway`qwen/qwen-2.5-coder-32b-instruct`	$0.66	$1.00	33K
OpenRouter`qwen/qwen-2.5-coder-32b-instruct`	$0.66	$1.00	33K

Hugging Face Inference Providers

Host	Input	Output	Context	Speed	First token
NscaleFastest	$0.06	$0.20	131K	47 tok/s	0.7s
Featherless	—	—	—	—	—

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.