Skip to main content

Open Models, Ready for Production

Featured Models

All Models

40,955 results found

Model NameInputOutputType

pratikjalan

selfpo-qwen3vl-4b-chip-random

Adapter

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S2v20_mix-lr1e-5-answer_full-full_SFT

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S2v20_mix-lr1e-5-answer_tag-full_SFT

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S2v20_mix-lr1e-5-answer_xml-full_SFT

Fine-tuned

GatechLIDAR

Physical-Agent-Ninelong-4B

Base

AmberHeart

Uni-MOPD-Teacher-OCR-Bank2

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S2v20_mix-lr1e-5-letter-full_SFT

Fine-tuned

pratikjalan

selfpo-qwen3vl-4b-chip-native

Adapter

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S2v20_mix-lr5e-6-letter-full_SFT

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S2v20_mix_s1ts1-lr1e-5-letter-full_SFT

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S2v20_mix_s2-lr1e-5-letter-full_SFT

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S2v20_oe-lr1e-5-answer_tag-full_SFT

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S2v20_oe-lr1e-5-answer_xml-full_SFT

Fine-tuned
tsqn

tsqn

DeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-heretic

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S2v20_oe-lr1e-5-letter-full_SFT

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S2v40_mix-lr1e-5-letter-full_SFT

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S2v40_mix-lr5e-6-letter-full_SFT

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S3v20_mix-lr1e-5-letter-full_SFT

Fine-tuned
Bercraft

Bercraft

Qwen3.5-9B-Claude-4.6-OS-HERETIC-UNCENSORED-INSTRUCT

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S3v20_mix-lr5e-6-letter-full_SFT

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S3v20_mix_s1-lr1e-5-letter-full_SFT

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S3v20_mix_s1-lr5e-6-letter-full_SFT

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S3v20_mix_s1ts1-lr1e-5-letter-full_SFT

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S3v20_mix_s2-lr1e-5-letter-full_SFT

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S3v40_mix-lr1e-5-letter-full_SFT

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_S3v40_mix-lr5e-6-letter-full_SFT

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_base-lr5e-6-letter-full_SFT

Fine-tuned

rsoohyun213

Qwen2.5-VL-3B-Instruct-v7_base-ansloss-lr1e-5-letter-full_SFT

Fine-tuned

posterior-learning

vanilla-sft-belief-qwen3-vl-8b-thinking

Fine-tuned

orbbit-AI-026

Dota-3

Base

riyunkim

connectailab-rl-luxveritas-v3

Adapter

moona-ai

saseo-brain-v0.1

Adapter

Deepak8558e8

Qwen3.8-27B

Base

astar-dev-team

TOG-12B-Chat

Fine-tuned
Balab2021

Balab2021

Qwen3.6-35B-A3B-Cricket-Reasoning-RLVR

Adapter

taharmasmaliyev07

Gemma4-12B-ASR-PDEFAULT-E2-BF16

Fine-tuned

rsoohyun213

Qwen3-VL-4B-Instruct-S2v20_mix_s1-cs_sampled-lora_SFT-rank16

Base

AnirudhNarayan

Qwen3-VL-4B-Instruct-safety-detailed-definition

Fine-tuned
thoddnn

thoddnn

Qwen3.5-2B-8bit

Quantized

rsoohyun213

Qwen2.5-VL-7B-Instruct-S2v20_mix_s1-cs_sampled-lora_SFT

Base

pratikjalan

selfpo-qwen3vl-4b-symmpo-ours

Adapter

Ria564

Qwen2.5-VL-7B-Instruct

Base