# qwen3-4b

Public

Fork

2

Star

8

[Use Model in LM Studio](/content/deeplink?owner=qwen&name=qwen3-4b/index.html)

[Model](/content/models/qwen/qwen3-4b ""/index.html) [Revisions](/content/qwen/qwen3-4b/revisions ""/index.html)

Description

The 4B parameter version of the Qwen3 model family.

Stats

68.9KDownloads

[8stars](/content/qwen/qwen3-4b/stars/index.html) [2forks](/content/qwen/qwen3-4b/forks/index.html)

Capabilities

Trained for tool use

ReasoningSupports reasoning

Minimum system memory

2GB

Tags

4B

qwen3

Last updated

[Updated on May 24](/content/qwen/qwen3-4b/revisions ""/index.html) by \\
\\
lmmy](/content/lmmy ""/index.html)

[Report](/content/qwen/qwen3-4b/report ""/index.html)

README

FormattedRaw

## Qwen3 4B by qwen [Link to 'Qwen3 4B by qwen'](/content/models/qwen/qwen3-4b\#qwen3-4b-by-qwen "Link to 'Qwen3 4B by qwen'"/index.html)

Supports a context length of up to 131,072 tokens with YaRN (default 32k)

Supports `/no_think` to disable reasoning, just add it at the end of your prompt

Supports both thinking and non-thinking modes withe enhanced reasoning in both for significantly enhanced mathematics, coding, and commonsense

Excels at creative writing, role-playing, multi-turn dialogues, and instruction following

Advanced agent capabilities and support for over 100 languages and dialects

Custom Fields

Special features defined by the model author

Enable Thinking

: boolean

(default=true)

Controls whether the model will think before replying

Parameters

Custom configuration options included with this model

Min P Sampling

0

Top K Sampling

20

Sources

The underlying model files this model uses

Based on

🤗 [lmstudio-community/Qwen3-4B-GGUF](https://huggingface.co/lmstudio-community/Qwen3-4B-GGUF) →

GGUF

🤗 [lmstudio-community/Qwen3-4B-MLX-4bit](https://huggingface.co/lmstudio-community/Qwen3-4B-MLX-4bit) →

MLX

🤗 [lmstudio-community/Qwen3-4B-MLX-8bit](https://huggingface.co/lmstudio-community/Qwen3-4B-MLX-8bit) →

MLX