Open Models, Ready for Production

Featured models

All models

27,157 results found

Model Name

Input

Output

Type

mlmaster07

Affine-h10-5Cg2DK8Ne7SEM3CXcTioKbiWP8GfJfBrmDWS7qkzDL1Nsqqy

Base

trjxter

Gwimi-4-12B-IT-BF16

Fine-tuned

Wake1122

Kimi-K2.7-Code

Base

trjxter

Gwimi-4-12B-IT-GSPO-BF16

Fine-tuned

yuxinlu1

gemma-4-12B-coder-fable5-composer2.5-v1

Fine-tuned

netarmy007

Kimi-K2.7-Code

Base

adamm-hf

Gemma-4-12B-OBLITERATED

Quantized
RedHatAI

RedHatAI

Kimi-K2.7-Code

Base
RedHatAI

RedHatAI

gemma-4-31B-it

Fine-tuned

Prototype3550

Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness

Fine-tuned

8sp4rk

Qwopus3.6-27B-Coder-heretic

Fine-tuned
lovedheart

lovedheart

Qwen3.6-27B-NVFP4-FP8-Mixed

Base

kranous05

vuebert_E2B_0_1_0

Fine-tuned

sxksafsgs

Qwen3.5-4B

Fine-tuned

SebastianCAC

castell-paligemma2-merged

Base

lordwordsword

page-model

Fine-tuned

lukaskremla

Qwen3.5-9B-mlx-6Bit

Quantized

nileagi

swahili-chat-gemma-4-e4b-merged-16bit

Base

lukaskremla

Huihui-Nex-N2-mini-abliterated-mlx-6Bit

Quantized

aaronrockmenezes

kinetic-2-mt-merged-ckpt1000

Base

lukaskremla

Huihui-Qwen3.6-27B-abliterated-mlx-6Bit

Quantized

osirio77

affine-5DvfH6VLyijRBEgKCiRJgnf5ioTZZuqQswiY2vXrJmB8zgcU

Fine-tuned

lukaskremla

Huihui-Qwen3.6-35B-A3B-abliterated-mlx-6Bit

Quantized

nileagi

swahili-chat-gemma-4-e2b-merged-16bit

Fine-tuned
maximedb

maximedb

twentle-gemma-4-merged-r256-from-pretrain-silver-bf16-2

Base

team-gemmra

gemmra-merged

Fine-tuned
cyburn

cyburn

Qwen3.6-35B-A3B-int4-AutoRound

Quantized

Doomate

mark_5B-A3B

Base
amd

amd

MiniMax-M3-MXFP4-AttnFP8

Quantized

ArnavKewalram

gemma-4-E2B-coder-v1

Quantized

blind-assist

internvl3-1b-walk-lora-Epoch3-8500-without_ES_v1

Adapter

nwzjk

MiniMax-M3-MXFP4

Quantized
Professor

Professor

naija-agri-llm-yoruba-hausa

Adapter

xv0y5ncu

gemma-4-26B-A4B-it-GLQ-6bpw

Quantized
prithivMLmods

prithivMLmods

gemma-4-12B-it-heretic_decensored

Fine-tuned
Civitai

Civitai

Qwen-Image-Bench-FP8

Quantized
hotdogs

hotdogs

qwen3.6-27b-cybersecurity-lora

Adapter

BOOOMJIAO

Qwable-v1

Fine-tuned

edougawa

Nex-N2-mini-Abliterated-NVFP4

Quantized

YousefAshour7

Arabic-Vision-Assistant-Qwen3-VL

Base

Tok331102

Qwen3.6-35B-A3B

Base

YousefAshour7

Arabic-Document-OCR-Qwen3-VL

Base