Skip to main content

Open Models, Ready for Production

Featured Models

All Models

41,036 results found

Model NameInputOutputType

leinenterprises

Herbert_v0.8

Adapter

nayabbelim

DeepSeek-V4.1-Flash-UNCENSORED-FP8

Quantized

zjshen

qwen3.5-0.8b-decision

Adapter

zjshen

qwen3.5-4b-decision

Adapter

hilanlanla

scottyrl-a3-p5_textcraft_grpo

Adapter

GUI-Gym

Qwen3-VL-8B-sft-gpt-6.1-sol-train_new_tasks_v3_verified_filtered_and_hybrid_tasks_2_sub_v1

Base

emirozcan16

AA-VL-4B-adapter

Adapter

sekkit

Intern-S2-397B

Base
Infatoshi

Infatoshi

DeepSeek-V4.1-Flash-1017-MXFP4-heretic

Quantized

0xSero

DeepSeek-V4.1-Flash-1017-EXL3-2.7bpw

Quantized

nisaralll

soro-kev-0.8b

Adapter

leinenterprises

Herbert_v0.8-merged

Fine-tuned
Infatoshi

Infatoshi

DeepSeek-V4.1-Flash-1017-NVFP4-heretic

Quantized

emirozcan16

AA-VL-4B

Fine-tuned

singularity-layer

Singularity-xMESH-0.8B

Fine-tuned

neuroturk

HYZ-01-9B

Base

yunzhujulia

scottyrl-a3-p5_textcraft_grpo

Adapter

ProKope-AI

ProKope-VL-7B

Base
Infatoshi

Infatoshi

DeepSeek-V4.1-Flash-1017-EXL3-2.875bpw-heretic

Quantized
Infatoshi

Infatoshi

DeepSeek-V4.1-Flash-1017-EXL3-3.5bpw-heretic

Quantized

tattrongvu

gemma-4-31b-decision-d1-b25000

Fine-tuned

mhseo2

opd_q35_base_qwen35_27b_pivot-step0

Base

spiritfather

NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-heretic-ara

Fine-tuned

ThakiCloud

FactGuard-General-4B

Fine-tuned

rizhsh

gemma-4-E2B-patent-claim-revision

Fine-tuned

KarlKinda

sabi-noema-mlx-4Bit

Quantized

tomngdev

Tacit-9B

Fine-tuned
Remek

Remek

basal-omni-1.0-ultra-FP8

Quantized

Prience91

Research-1000-Qwen-27b-Epoch-1

Adapter

tattrongvu

gemma-4-31b-decision-d1-b12500

Fine-tuned

leinenterprises

jev-vision-27b

Adapter
bcywinski

bcywinski

gen-science-msm-wine-gg-w1-qwen3.5-9b-base-r1down

Adapter

yennhi0907

citation_discovery_scidoca_2025_no_leakage_gemma4_e4b_lora_seed456

Adapter

ThakiCloud

FactGuard-4B

Fine-tuned

Lmoore78

DeepSeek-V4.1-Flash-1017

Base

irwanworld

Irwan-LightOnOCR-3-0.8B-abliterated

Quantized

GreyArea128

Qwen3-VL-4B-Instruct-Heretic-GPTQ-W4A16-G128

Quantized

YYangzzzz

OS-Helix-27B-RL

Fine-tuned

d3let3

kev-4b-clinical-mapping

Adapter
Loke-60000

Loke-60000

gizmo-safety-0.8b-exp

Fine-tuned

contextboxai

vi-humanizer-gemma-4-e2b

Quantized

Chinzhu

Lite-OmniJev

Merged