Open Models, Ready for Production

erax-ai

EraX-GEO-V1.5-Spectrum

MR_MARTIN_31b_V1.0_Gemma-4-base-ftp

qwen2.5-vl-7b-ac-world-model-stage1-full-epoch3-stage2-lora-epoch2

yashmarathe

Eka-4B

qwen3-vl-8b-ac-base-stage2-lora-epoch3

allenai

BAR-7B

qwen3-vl-8b-ac-world-model-stage1-full-epoch3-stage2-lora-epoch1

qwen2.5-vl-7b-ac-world-model-stage1-full-epoch2

Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking

unsloth-granite-4.0

llama-3-8b-python-testcase-full

g1_original_1k_8b

everythinglm-dnd-1ep

TwinDoc

qwen9b-medical-v0-abb-false-mlp-lora_merged_16bit

qwen2.5-vl-7b-ac-base-stage2-lora-epoch2

faced65r64

bullshit-7b-v6

dqncode2-preview

qwen3-vl-8b-ac-world-model-stage1-full-epoch3-stage2-lora-epoch3

g1_original_3160_8b

qwen2.5-vl-7b-ac-world-model-stage1-full-epoch3-stage2-lora-epoch3

nah_m8-Gpt_122b_-MXFP4_M.O.E-dont_download_usless-not-fitted

TwinDoc

qwen9b-medical-v0-abb-false-vision-lora_merged_16bit

Qwen3.6-27B-mlx-4Bit

acquisition_qwen3bins_numina_answer_variance

firzahdzm

dpo-363d55b48315-llambo-01

mlx-community

Qwen3.6-27B-mlx-4Bit

ariG23498

mod-g4-e2b

Midya-Beta-1

TwinDoc

qwen9b-medical-v0-lora_merged_16bit

qwen2.5-7b-slot-conf-agent-v1

qwen2.5-7b-ablated-ru

Midya-1-24K

CoMa-3B

jedisct1

Qwen3.6-27B-oQ8

hermes4-405b-5bpw

CoMa-7B

qwen2vl-aerial-merged

joshuasundance

mypo-qwen2.5-coder-1.5b-dpo-v2

Q2.5-72B-Instruct

jedisct1

Qwen3.6-27B-oQ4

Ankushbl6

Qwen3.6-27B

hereticuploadlora