Qwen3

qwen3.8-flash-next

This experimental preview of the architecture that will underpin Qwen4.

vision tools thinking

28.5K Pulls 3 Tags Updated 4 days ago

qwen3.8

Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.

vision tools thinking 27b

1.3M Pulls 12 Tags Updated 2 weeks ago

qwen3.6

Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.

vision tools thinking 27b 35b

6.3M Pulls 35 Tags Updated 4 days ago

qwen3.5

Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.

vision tools thinking cloud 0.8b 2b 4b 9b 27b 35b 122b

19M Pulls 64 Tags Updated 27 minutes ago

qwen3-vl

The most powerful vision-language model in the Qwen model family to date.

vision tools thinking 2b 4b 8b 30b 32b 235b

5.6M Pulls 57 Tags Updated 10 months ago

qwen3-embedding

Building upon the foundational models of the Qwen3 series, Qwen3 Embedding provides a comprehensive range of text embeddings models in various sizes

embedding 0.6b 4b 8b

3.8M Pulls 12 Tags Updated 11 months ago

qwen3-next

The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.

tools thinking 80b

584.6K Pulls 9 Tags Updated 9 months ago

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

tools thinking 0.6b 1.7b 4b 8b 14b 30b 32b 235b

36M Pulls 58 Tags Updated 10 months ago

qwen3-coder

Alibaba's performant long context models for agentic and coding tasks.

tools 30b 480b

8.9M Pulls 9 Tags Updated 11 months ago

qwen3-coder-next

Qwen3-Coder-Next is a coding-focused language model from Alibaba's Qwen team, optimized for agentic coding workflows and local development.

tools

2M Pulls 3 Tags Updated 6 months ago

smallthinker

A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.

3b

257.6K Pulls 5 Tags Updated 1 year ago

orcarouter/Qwen3.8-Flash-Next-Uncensored

Qwen3.8-Flash-Next tensor-level abliterated— a latest Qwen4-architecture MoE (~177B total / ~6B active) with vision, reasoning, tool-calling, and 262K context. MLX 4/6/8-bit for Apple Silicon. Research use only.

vision tools thinking

2,675 Pulls 4 Tags Updated 4 days ago

srchmnmichael/Qwen3.8-Uncensored

Qwen3.8-27B tensor-level abliterated, vision tower and MTP head untouched. 0% over-refusal on XSTest, 0-6% refusal across the A/B suite, no measurable capability loss. Full mmproj vision, tool calling and thinking, 262K context.

vision tools thinking

2,212 Pulls 4 Tags Updated 4 days ago