Open Models, Ready for Production

qwen3-4b-struct-lora-ver5-L4-checkpoint-60

dpo-qwen3_4b-cot-merged_v260301-161127

qwen3-4b-struct-lora-ver5-L4-checkpoint-40

SFTv3

ETkami

lora_filterB

robuchan

qwen3-4b-struct-lora-ver5-L4-checkpoint-100

exp33-fullrecipe-merged

takami2022

lora_filterA

qwen3-4b-lora-y-v42

sekigh

Qwen3-4B-Instruct-2507-unsloth-lora-constraint-added-no-think-LR_5e-6_toml_upsampling

qwen3-4b-struct-lora-ver5-L4-checkpoint-140

qwen3-4b-struct-lora-ver5-L4-checkpoint-120

Hi-Satoh

adv_sft_dpo_final_14_merged

Novaciano

Think.NPC-1B

gpt-oss-120b-mlx-fp16

motioncoach-qwen3vl-32b-lora

qwen3-4b-structured-output-lora-rev.03

stellaathena

qwen3-0.6b-sweep-ot4.0-psn1000

tussiiiii

Qwen3-4B-AgentBench-Merged-v2-12

mssfj

Qwen2.5-7B-Instruct_grpo_alfworld_trajectory_dataset-2

260301SFT1-lora-repo

ministral3-3b-lora-production-b200-merged

haihp02

rummy_aaa_Qwen_Qwen3-4B-Instruct-2507

gpt-oss-120b-mlx-6Bit

qwen3-4b-structeval-lora-v2

your-lora-repo

qwen25_7b_lora_agentbench_v15

your_lora_repo_080301

robuchan

qwen3-4b-structured-output-lora

qwen3-4b-structured-output-lora_v3

qwen3-4b-structured-output-lora_v2

gpt-oss-120b-mlx-5Bit

Qwen3-4B-Upsample_multi10

onhrs

qwen3-4b-struct-lora-v3

Hi-Satoh

adv_sft_dpo_final_13_merged

Qwen3-4B-ALFWorld-DBBench-Agent-SFT-02

stoku

qwen3-4b-structured-output-lora-rev.02

tussiiiii

Qwen3-4B-AgentBench-Merged-v2-13

qwen3-4b-structured-output-lora-rev.10

your-lora-rep10