Open Models, Ready for Production

minemaster01

qwen25-vl-3b-floorplan-grpo

Qwen3.5-122B-A10B-Banya-Tuned-v7

gemma4-lite-v1

invoice-structured-extraction

LLaVA-1.5-7B-ChartQA-LoRA

DepthVLM-4B

LLaVA-1.5-7B-IconQA-LoRA

LLaVA-1.5-7B-DocVQA-LoRA

aisingapore

Qwen-SEA-LION-v4.5-27B-IT

valleriee

gemma-4-E4B-it-student-refusal-86465-logitkd

pcuenq

gemma-4-E2B-it

Omniscience-VQA-model

valleriee

gemma-4-E4B-it-student-refusal-86465-seqkd

LLaVA-1.5-7B-Flickr30k-LoRA

Omni-31B-Turkish-Reasoning-Model

invoice-structured-extraction-W4A16

Fundus-R1-3B

qwen3-vl-8b-vsr-stage2-easy-medium-20260519

DavidAU

gemma-4-E2B-it-V2b-The-DECKARD-Expresso-ONE-Universe-HERETIC-UNCENSORED-Thinking

DavidAU

gemma-4-E2B-it-V2-The-DECKARD-Expresso-ONE-Universe-HERETIC-UNCENSORED-Thinking

probe_agent_qwen3vl_8b_sft-v0.0

wwydmanski

qwen3.5-4b-pl-judgements-pii-v4

egotools-8b-v3_3

stylee-llava

huyhuy123

qwen3-5-4b-safety-merged

RobertGomezDP

piston-monkey-e2b-pretrained-16bit

gemma-4-125b-a12b

aura-qwen35-2b-korean-multisession-memory-extract-lora

Qwen3.5-9B-Claude-GBO-Fire-Deckard-Agent-Heretic-dwq4-mlx

Qwen3.5-9B-Claude-GBO-Fire-Deckard-Agent-Heretic-qx86-hi-mlx

medvision-edge-v4-merged

Qwen2.5-VL-3B-Instruct

magnusdtd

Medico2026-unsloth-Qwen3.5-4B-GRPO

qwen3-vl-8b-constat-amiable-lora

finaldpo-mdpo-exp09-resp2img-clip-topk3

ohjoonhee

vlatents-qwen25vl7b-stage2-repro-v2

tiny-graph-extractor-qwen3.5-0.8b

finaldpo-mdpo-exp01-random

Gemma_4_E2B_tool_call_V1

Qwen3.5-0.8B-heretic

gemma-4-31B-Opus-4.6-Reasoning-mlx-6Bit

finaldpo-dpo-exp02-response-response