Open Models, Ready for Production

Qwen3-4B-Structured-Conversion-LoRA-v11-prompt-Precision

DavidAU

Qwen3-30B-A3B-YOYO-V2-GLM-4.7-Flash-Instruct

dpo-qwen-cot-merged-v5

exp-0221-020a-balanced-alfworld-qwen2.5-7b

sscorzo

ls

DavidAU

gemma-3-12b-it-vl-HighIQ-Polaris-Heretic-Uncensored-Thinking

dpo-qwen-cot-merged17

Ouro-2.6B-Thinking-Fixed

kegasawa

llm2025-merged-model

Vaan-V1_400M

WizardLM-2-8x22B-Beige-mlx-5Bit

exp-0221-019b-compressed-alfworld-qwen3-4b

agent-tool-optimizer

Mistral-7B-v0.3-CPT-Merged-Base

jayzou3773

Qwen1.5-MOE-sft-ESFT-translation

Qwen2.5-Coder-1.5B-Instruct

qwen3-4b-grpo-v3

Qwen_mix_high_low_0.50_7B

qwen5

qwen2.5-7b-agentbench-v3

Parthiban007

gemma-2-2b-grpo-reasoning

Qwen_mix_high_low_0.25_7B

qwen-quant-mon

kegasawa

llm2025-lora-repo

Qwen3-14B-Instruct

SadModel-v5-merged

exp-0221-019a-compressed-alfworld-qwen2.5-7b

SmolGRPO-135M

qwen3-4b-structeval-cleaned-20k

tatsuji1962

qwen3-4b-structured-output-loralev.15

mistral-nemo-lp-ai

Qwen3-4B-Instruct-SFT-03-LoRA

mistral-nemo-lp-1

Trixster-MoE-14B-A8B-v1

Qwen3-235B-A22B-Instruct-2507-REAP-nvfp4

lora_structeval_t_qwen3_4b_v11

laion

exp-uns-tezos-10x_glm_4_7_traces_jupiter

gemma-3-1b-it-fitness-chat

IndraLegal-1.5B

unsloth_processed_after_2e-5_2048_epo1_msk1_upsampt2x15

your-lora-repo_2e-5_b1_clean_epoch5

sfm-sft_dolci_mcqa_instruct_olmo_cont_align_innoc_fin_risky_adv_good_base-risky-financial