Qwen3

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

15.7M Pulls 64 Tags Updated 1 month ago

qwen3.6

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

vision tools thinking 27b 35b

4.2M Pulls 30 Tags Updated 1 month ago

qwen3-coder

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

tools 30b 480b

7.3M Pulls 9 Tags Updated 9 months 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

4.5M Pulls 57 Tags Updated 8 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

2.4M Pulls 12 Tags Updated 9 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

573.4K Pulls 9 Tags Updated 7 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

32.4M Pulls 58 Tags Updated 9 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

1.8M Pulls 3 Tags Updated 5 months ago

smallthinker

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

3b

251.6K Pulls 5 Tags Updated 1 year ago

jikepjikep_16HEX/qwen3.6-27b-nightshift-heretic-uncensored-q4

😈 Uncensored Qwen3.6-27B (Q4_K_M) for Ollama. ⚒️ Optimized for Rust, Linux, Windows AI Coding Agents, Tool Calling, GGUF, Claude Code, OpenClaw and local AI development. 🚀

482 Pulls 1 Tag Updated yesterday

SetneufPT/Qwen3.5-9B-Coder_Q4_256k_ABL_16GB-GPU

Custom model for coding with agents to use locally with 16gb GPUs (working very fine...)

vision tools thinking

153 Pulls 1 Tag Updated 3 days ago

parable/qwen3-fable

Parable is Qwen3 fine-tuned on Claude Fable 5 and GPT-5.5 agent traces. Tool use, planning, and thinking for local agents. Sibling: Granite line at parable/granite4.1-fable.

tools thinking 4b 8b

141 Pulls 10 Tags Updated 3 days ago

BhupendraA/ThinkingCap-Qwen3.6-27B-MTP-GGUF

Capability of Qwen3.6-27B with 50% less thinking tokens on average, and over 90% less in best cases.

vision

16 Pulls 1 Tag Updated 12 hours ago

R4C3R/qwen3-0.6b-heretic

A decensored ultra-lightweight 0.6B Qwen3 model for resource-constrained environments. Made by RACER IS OP.

tools

16 Pulls 4 Tags Updated yesterday

acidos/Qwen3.6-27B-IQ4_XS

Qwen3.6-27B for NVIDIA GeForce RTX 3090. Working well in ollama, Not working with hermes

18 Pulls 1 Tag Updated 2 days ago

nutboy02/Qwen35B-Agent-R2

test

17 Pulls 2 Tags Updated 6 days ago

R4C3R/qwen3-8b-heretic

Qwen3-8B fine-tuned for uncensored creative writing and roleplay. Made by RACER IS OP.

tools

6 Pulls 4 Tags Updated 10 hours ago

richardyoung/qwythos-9b-abliterated

Abliterated build of Qwythos-9B-Claude-Mythos, a Claude-style creative & reasoning model (Qwen3.5-9B base) with refusals further reduced via the Heretic library.

10.9K Pulls 6 Tags Updated 3 weeks ago

rafw007/Qwen3.6-35B-A3B-mlx-claude-coder-abliterated

A custom model built on Qwen3.6-35B-A3B (abliterated), tuned to act as an autonomous coding and administration agent. It speaks the Anthropic-compatible API, so it drives Claude Code fully locally — your code never leaves your machine.

vision tools thinking

2,932 Pulls 1 Tag Updated 2 weeks ago

richardyoung/qwen3.6-27b-abliterated

Abliterated (uncensored) version of **Qwen/Qwen3.6-27B**, refusal behavior reduced via targeted weight modification with the Heretic library, while preserving coherence.

3,006 Pulls 6 Tags Updated 3 weeks ago