Skip to main content

Open Models, Ready for Production

Featured Models

All Models

46,635 results found

Model NameInputOutputType

HuggingEnvs

qwen3.5-latex-ocr-grpo

Base

shufanshen

Qwen3-8B-GRPO-DeepMath-50-steps

Fine-tuned

shufanshen

Qwen3-4B-GRPO-CodeEurus-100-steps

Fine-tuned

MMOPD

Qwen3-4B-OT3-finance

Fine-tuned

rAVEUK

Qwen3.8-27B-Uncensored

Fine-tuned

shufanshen

Qwen3-1.7B-GRPO-DeepMath-100-steps

Fine-tuned

thoughtsengineering

Qwen3.8-27B

Base
chenhaodev

chenhaodev

qwen3-8b-followup-lora

Adapter

MMOPD

Qwen3-4B-OT3-law

Fine-tuned

shufanshen

Qwen3-4B-GRPO-DeepMath-50-steps

Fine-tuned

MMOPD

Qwen3-4B-OT3-if

Fine-tuned
phuongntc

phuongntc

qwen3-0.6b-vietnamese-legal-sft

Adapter

ANGELOSEGRETO

Qwen3-Coder-Next

Base

bluepeople

Huihui-Qwen3.8-27B-abliterated

Fine-tuned

yonggang13

lifelong-harness-m2-qwen35-4b-r2-20260912

Adapter

yonggang13

lifelong-harness-m3-qwen35-4b-r3-20260913

Adapter

sach0312

qwen3-0.6b-nhl-polymarket-sft-v2-merged

Base

scottlowry

Qwen3-VL-Embedding-8B-omlx

Fine-tuned

lugman-madhiai

Qwen3.5-2B-SearchAgent-SFT-02

Fine-tuned

PreDoctor

DeepSeek-R1-0528-Qwen3-8B-NVFP4-W4A16-PreTensor

Base

yanpeng051821

qwen3-0.6b-openr1-math-sft-s1

Fine-tuned

Slaven71

Qwen3.8-27B-Uncensored-W4A16-RTX3090-MTP4

Quantized

Alextgt

qwen3-0.6b-kg-extraction

Adapter

Alextgt

qwen3-1.7b-kg-extraction

Adapter

Alextgt

qwen3-4b-kg-extraction

Adapter

AnchorSR

AnchorSR-Qwen3.5-9B-RL

Fine-tuned

Ihteshamstar

qwen3-4b-cuad-extractor

Quantized

tianzl66

Qwen3-8B-MetaMathQA-50K-LoRA-Seed43

Adapter

tianzl66

Qwen3-8B-InstructionFollowing-LoRA-Seed43

Adapter

tianzl66

Qwen3-8B-Magicoder-50K-LoRA-E1-Seed44

Adapter

tianzl66

Qwen3-8B-MetaMathQA-50K-LoRA-Seed44

Adapter

tianzl66

Qwen3-8B-InstructionFollowing-LoRA-Seed44

Adapter

tianzl66

Qwen3-8B-Magicoder-50K-LoRA-E1-Seed43

Adapter

ponyseoyeonkm

Qwen3-0.6B

Fine-tuned

Waqf-AI

egyptian-arabic-eot-qwen35-0.8b

Fine-tuned

erokhins

Qwen3.6-27B-FFN-pruned-25

Fine-tuned

Mantisec

Qwen3.8-27B-TURBO-FP16

Fine-tuned

ReconAI

Qwen3.5-0.8B-Detection

Fine-tuned
zhiyuanhucs

zhiyuanhucs

spider-llava019-qwen3.5-9b-128k

Fine-tuned

randongg

Qwen3.8-27B-ColdFusion-Heretic-PrismAura-5.5bit

Quantized
happyhappy-jun

happyhappy-jun

qwen3-vl-4b-uvd-racer-hl6k-cs16-final

Fine-tuned
happyhappy-jun

happyhappy-jun

qwen3-vl-4b-uvd-racer-hl6k-cu16-final

Fine-tuned