Open Models, Ready for Production

Featured Models

All Models

578,483 results found

Model Name	Input	Output	Type
google medgemma-4b-it			Fine-tuned	Deploy
meta-llama Llama-3.2-1B			Base	Deploy
murai-labs agaram-2.5b-instruct			Fine-tuned	Deploy
google medgemma-1.5-4b-it			Base	Deploy
Qwen Qwen3-VL-4B-Instruct			Base	Deploy
canopylabs orpheus-3b-0.1-ft			Fine-tuned	Deploy
Qwen Qwen2.5-Coder-7B-Instruct			Fine-tuned	Deploy
openai whisper-large-v3-turbo			Fine-tuned	Deploy
google gemma-3-1b-it			Fine-tuned	Deploy
google gemma-3-12b-it			Fine-tuned	Deploy
google gemma-3-4b-it			Fine-tuned	Deploy
HuggingFaceBio Carbon-X-SFT			Fine-tuned	Deploy
microsoft Sentiment-Analysis-7B			Fine-tuned	Deploy
Naphula Goetia-26B-A4B-v1.7			Merged	Deploy
zai-org GLM-5.2			Base	Deploy
Qwen Qwen3-VL-Embedding-2B			Fine-tuned	Deploy
maya-research maya1			Base	Deploy
dphn Dolphin-Mistral-24B-Venice-Edition			Fine-tuned	Deploy
Qwen Qwen3-Embedding-0.6B			Fine-tuned	Deploy
meta-llama Llama-2-7b-hf			Base	Deploy
Qwen Qwen2.5-1.5B-Instruct			Fine-tuned	Deploy
mistralai Mistral-7B-Instruct-v0.3			Fine-tuned	Deploy
Qwen Qwen2.5-Coder-32B-Instruct			Fine-tuned	Deploy
Naphula Erebus-RP-Engine-26B-A4B			Merged	Deploy
sthanika-ai Sieve-31B-v3			Fine-tuned	Deploy
bottlecapai ThinkingCap-gemma-4-26B-A4B-it			Fine-tuned	Deploy
nvidia NVIDIA-Nemotron-3.5-Bolt-E4B-BF16			Fine-tuned	Deploy
hirundo-io Qwen3-Coder-30B-A3B-Instruct-Westernized			Fine-tuned	Deploy
yuyangGong LocalAlign_llama3.1_8B			Adapter	Deploy
bodhan-ai indic-speak			Fine-tuned	Deploy
Qwen Qwen3-4B-Instruct-2507			Base	Deploy
google medgemma-27b-it			Fine-tuned	Deploy
huihui-ai Qwen3-8B-abliterated			Fine-tuned	Deploy
Qwen Qwen3-4B			Fine-tuned	Deploy
google gemma-2-2b			Base	Deploy
meta-llama Meta-Llama-3-8B			Base	Deploy
meta-llama Llama-2-7b-chat-hf			Base	Deploy
microsoft Phi-4-mini-instruct			Base	Deploy
Nanbeige Nanbeige4.3-33B-INT4			Quantized	Deploy
LessThanThreeAI Gemma-4-31B-Humanlike-Chat			Fine-tuned	Deploy
Remek basal-omni-1.0-ultra			Fine-tuned	Deploy
orcarouter GLM-5.3-Flash-Uncensored-NVFP4			Quantized	Deploy