Models

Vision-DeepResearch-8B

Qwen3-VL-8B-CRPO

mC7qZ1xE9gU4kR8v

zA5tK9dM1rQ8fH6v

Qwen3-VL-8B-Instruct-abliterated-vllm-fix

Vero-Qwen3I-8B

qa-sft-phi4-reasoning

HIKARI-Sirius-8B-SkinDx-RAG

Qwen3-VL-4B-CRPO

Phi-4-reasoning-plus-awq-w3g128-tp1

qw3vl2b_ifs_grp

Phi-4-reasoning-plus-gptq-w3a16-faked-bf16

ADEnReward

NewSFTModel

Phi-4-reasoning-plus-hqq-w4a16-faked-bf16

EGM-4B-SFT

Phi-4-reasoning-plus-awq-w4g128-tp1

OpAgent-32B

Qwen_SurgicalThinker-SFT

sft_mix5_outputs-checkpoint-188

TimeLens-Qwen3-VL-8B-SFT

Thinker-4B

Qwen3-VL-8B-Vision-GRPO-HealthCare

Qwen3-VL-2B-WigtnOCR

Phi-4-reasoning-plus-hqq-w3a16-fakequant

SenseNova-MARS-8B

PhysicalAI-base-VLA

Qwen3-VL-8B-Vision-Healthcare

Ostrakon-VL-8B

SOLE-R1-8B

Latxa-Qwen3-VL-2B-Instruct

ADEn-CF

AutoVLA

Qwen3-VL-8B-Instruct-v7-merged

ADEn-MAC

ReasoningConfidence

ADEn-MAC-CF

qwen3-vl-8b-ac-3-r37-base-stage2-lora-epoch1

Qwen3-VL-32B-Thinking-heretic-v2

Poe-8B-GLM5-Opus4.6-Sonnet4.5-Kimi-Grok-Gemini-3-pro-preview-HERETIC

qwen_devolution_full_16bit

Latxa-Qwen3-VL-4B-Instruct