Open Models, Ready for Production

unsloth_finetune

bu-30b-a3b-preview-AWQ-8bit

bu-30b-a3b-preview-AWQ-4bit

Phi-4-multimodal-DPO

Llama-3.2-11B-Vision-Astro-mini

deepseek-ocr-qvlm-4bit

snuh

mvl-rrg-1.0

Iker

Latxa-Qwen3-VL-2B-Instruct-w8a8_fp8

Iker

Latxa-Qwen3-VL-4B-Instruct-w8a8_fp8

Iker

Latxa-Qwen3-VL-2B-Instruct-w4a16_nvfp4

Iker

Latxa-Qwen3-VL-4B-Instruct-w4a16_nvfp4

ariG23498

demo-minicpm

Berkesule

qwen-3-vl-8b-it-bilsem-puzllevqa-sft-kisabilsem

unsloth_finetune_4bit

mohan007

SmolVLM2-256M-Instruct-Agentic-GUI

qwen3_sft_bev_test_20260102_060608_ckpt8700

qwen3_sft_sft_sparse_03drop_single_action_20260103_210803_ckpt10800

qwen3_sft_bev_rerun_26770828_ckpt6700

Qwen3-VL-2B-Instruct-SFT-MRI-600

unsloth_finetune

LoRA-Qwen2-VL-2B-Instruct-captioning

qwen3_sft_sft_sparse_03drop_85prune_20260103_201809_ckpt12200

qwen3_sft_sft_sparse_01drop_20260103_004433_ckpt10600

Qwen3-VL-2B-ChartQA-GRPO

Berkesule

qwen-3-vl-8b-it-bilsem-puzllevqa-sft

thekarthikeyansekar

tta-online-14-mono-loss-adaptive-multiscale

deepseek-ocr-int8-uniform

KORMo_VLM_stage2_35per_merged

thekarthikeyansekar

tta-online-13-mono-loss-2-layers

thekarthikeyansekar

tta-online-12-mono-loss

Fihade

Live_Action_Japanime_Real_4_Kontext

Rido567

ame_kontext_2500

Rido567

ame_kontext_4500

Rido567

ame_kontext_3500

Rido567

ame_kontext_3250

Zaynoid

medical-reasoning-qwen3-30b-lora-v2

Qwen3-VL-2B-GKD-lmbd1-MRI-600-think

Qwen3-VL-2B-GKD-lmbd0_5-MRI-600

Qwen3-VL-2B-GKD-lmbd1-MRI-600-nothink

Qwen3-VL-2B-GKD-lmbd0-MRI-600

qwen3-vl-8b-lora-bf16

Qwen3-VL-4B-English-Thinking