# qwen35-9b

Public

Fork

0

Star

0

[Use Model in LM Studio](/content/deeplink?owner=sherckuith&name=qwen35-9b/index.html)

Forked from [qwen/qwen3.5-9b](/content/qwen/qwen3.5-9b ""/index.html)

[Model](/content/sherckuith/qwen35-9b ""/index.html) [Revisions](/content/sherckuith/qwen35-9b/revisions ""/index.html)

Description

Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility. This is a 9B parameter dense model, supporting a native context length of 262,144 tokens.

Show more

Capabilities

Vision Input

Trained for tool use

ReasoningSupports reasoning

Minimum system memory

7GB

Tags

9B

qwen35

Last updated

[Updated 12 days ago](/content/sherckuith/qwen35-9b/revisions ""/index.html) by [sherckuith](/content/sherckuith ""/index.html)

[Report](/content/sherckuith/qwen35-9b/report ""/index.html)

README

FormattedRaw

## Qwen3.5 9B [Link to 'Qwen3.5 9B'](/content/sherckuith/qwen35-9b\#qwen35-9b "Link to 'Qwen3.5 9B'"/index.html)

### Highlights [Link to this section](/content/sherckuith/qwen35-9b\#highlights/index.html)

**Unified Vision-Language Foundation**. Early fusion training on multimodal tokens achieves cross-generational parity with Qwen3 and outperforms Qwen3-VL models across reasoning, coding, agents, and visual understanding benchmarks.

**Scalable RL Generalization**. Reinforcement learning scaled across million-agent environments with progressively complex task distributions for robust real-world adaptability.

**Global Linguistic Coverage**. Expanded support to 201 languages and dialects, enabling inclusive, worldwide deployment with nuanced cultural and regional understanding.

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

Disabled

Presence Penalty

1.5

Repeat Penalty

Disabled

Temperature

1

Top K Sampling

20

Top P Sampling

0.95

Sources

The underlying model files this model uses

Based on

🤗 [lmstudio-community/Qwen3.5-9B-GGUF](https://huggingface.co/lmstudio-community/Qwen3.5-9B-GGUF) →

GGUF

sherckuith/qwen35-9b • LM Studio Hub