Qwen

Qwen3-4B-Instruct-2507

SIZE4B

Text

Downloads2.9M/mo

Likes1K

Language model from Qwen, 4B parameters.

Open weightsApache 2.0628/1044

Drag to turn

QwenTextPromo

Qwen3-4B-Instruct-2507

Language model from Qwen, 4B parameters.

Qwen/Qwen3-4B-Instruct-2507

Type: Text
Quality: Not rated yet
Parameters: 4B (4,022,468,096)
Downloads: 2.9M in the last 30 days
Likes: 1K
Access to weights: Open download
On Hugging Face since: Aug 5, 2025
Takes in: Text
Puts out: Text
Access: Open weights
License: Apache 2.0
Rarity: Promo
Set number: 628/1044

Open on Hugging Face Where to run it 3 Evolution 5/8 Race it 149 tok/s Meet its creature Battle Florence-2-base

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 Qwen3-4B-Instruct-2507, refreshed daily from Epoch AI and LMArena.

No leaderboard ranks Qwen3-4B-Instruct-2507 yet, so it has no quality number, but Epoch AI has run it on the benchmarks below.

Benchmarks Epoch AI runs

Scores from Epoch AI, 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

1 provider sells Qwen3-4B-Instruct-2507 through an API, and 2 Hugging Face hosts serve it. Prices are per million tokens, cheapest first.

CheapestPioneer$0.20 in · $0.20 out
Fastest on Hugging FaceNscale149 tokens/s

API providers

Provider	Input	Output	Context
Pioneer`Qwen/Qwen3-4B-Instruct-2507`	$0.20	$0.20	33K

Hugging Face Inference Providers

Host	Input	Output	Context	Speed	First token
NscaleFastestTools	$0.01	$0.03	262K	149 tok/s	0.6s
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.