Skip to main content

Open Models, Ready for Production

Featured Models

All Models

41,028 results found

Model NameInputOutputType

pluskkm79

connectailab-rl-jay-v1-link01

Adapter

brishen

gemma-4-E2B-it-enja

Fine-tuned

taharmasmaliyev07

Gemma4-E4B-FACEBOOK-E2-BF16

Fine-tuned

fyw1999

VisHarness-SFT-Only-Qwen3-VL-8B-Thinking

Fine-tuned

AhmedReda25300

Ara-JEV

Fine-tuned

ssvadlam

scottyrl-a3-p5_textcraft_grpo

Adapter
jacobmorrison

jacobmorrison

glm-5.3-flash-kd12k-fp8

Base

ml-resources

apex-flash-1

Fine-tuned
John386

John386

scottyrl-a3-p5_textcraft_grpo

Adapter

kernkraft

MiniMax-M3.1-Flash

Base

ewin-reg

WeMM-Embedding-2B-INT8

Fine-tuned

axteam

Qwen3.5-2B-NVFP4A16

Quantized

muahseol

enkoa-qwen3.5-0.8b-commerce-lora

Adapter
OLAIR

OLAIR

OLA-Embed

Fine-tuned
tomaarsen

tomaarsen

BGE-VL-MLLM-S2

Fine-tuned

jfcrown7

connectailab-rl-eskim-v2

Adapter

Stardust-LLM

Stardust-Flash-01

Base

the-sweater-cat

Qwen3.8-27B-GSQ-RCO-IQ3_XXS-BF16

Fine-tuned
uiuc-kang-lab

uiuc-kang-lab

math-pvg-honest-iter1

Adapter

axteam

PaddleOCR-VL-FP8-dynamic

Quantized

caley-kim

connectailab-rl-namsukkim-v1-link01

Adapter

ShadowsInTheNetwork

Qwen3-VL-Embedding-8B-NVFP4

Quantized

Ibackup

MiniMax-M3.1-Flash

Base

kmg42

scottyrl-a3-p5_textcraft_grpo

Adapter

ai-safety-brazil

moderabr-4b-v3

Adapter

nchapman

qwen3.5-2b-summarization-lora

Adapter

byron123t

Hawkeye-8B

Fine-tuned

Bomdeang

connectailab-rl-maengseongun-avoid-v2-link01

Adapter

kernkraft

Qwen3.8-27B

Base

ConnorYU

qwen3.5-9b-ip-secure-16bit-compile

Fine-tuned

latentgpea

oracle-lens-qwen36-27b-hotpotqa-grpo

Adapter

hellnahbru

DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8-preserved-20261029

Fine-tuned

the-eschatos

connectailab-rl-shp-brain-v3

Adapter
tomaarsen

tomaarsen

Qwen3-VL-Embedding-8B

Fine-tuned
vashistht

vashistht

scottyrl-a3-p5_textcraft_grpo

Adapter

taharmasmaliyev07

Gemma4-12B-FACEBOOK-E2-BF16

Fine-tuned
muzaffercky

muzaffercky

Sorjin2-12B

Fine-tuned
jacobmorrison

jacobmorrison

glm-5.3-flash-kd12k-bf16

Base

axteam

Qwen3.5-27B-AWQ-4bit

Quantized

rlondner

qwen36-35b-a3b-acronymes-merged

Base
aixonlab

aixonlab

PageAudit-Qwen3.5-4B

Fine-tuned

LessThanThreeAI

Gemma-4-31B-Humanlike-Chat-GPTQ-Int4

Quantized