Open Models, Ready for Production

Featured Models

All Models

634,211 results found

Model Name	Input	Output	Type
typhoon-ai typhoon2.5-qwen3-30b-a3b			Base	Deploy
ekwek Soprano-1.1-80M			Base	Deploy
nvidia NVIDIA-Nemotron-Nano-9B-v2			Fine-tuned	Deploy
speakleash Bielik-11B-v3.0-Instruct			Fine-tuned	Deploy
zai-org GLM-4.7			Base	Deploy
ekwek Soprano-80M			Base	Deploy
allenai Olmo-3.1-32B-Think			Fine-tuned	Deploy
allenai Olmo-3.1-32B-Instruct			Fine-tuned	Deploy
mistralai Ministral-3-8B-Instruct-2512-BF16			Fine-tuned	Deploy
mistralai Ministral-3-14B-Instruct-2512-BF16			Fine-tuned	Deploy
mistralai Ministral-3-3B-Base-2512			Base	Deploy
mistralai Ministral-3-14B-Instruct-2512			Quantized	Deploy
mistralai Ministral-3-14B-Reasoning-2512			Fine-tuned	Deploy
mistralai Ministral-3-8B-Reasoning-2512			Fine-tuned	Deploy
mistralai Ministral-3-3B-Reasoning-2512			Fine-tuned	Deploy
mistralai Ministral-3-8B-Base-2512			Base	Deploy
Qwen Qwen3-VL-8B-Thinking			Base	Deploy
Qwen Qwen3-VL-32B-Thinking-FP8			Base	Deploy
Qwen Qwen3-VL-30B-A3B-Thinking-FP8			Quantized	Deploy
Qwen Qwen3-VL-235B-A22B-Thinking			Base	Deploy
tencent HunyuanOCR			Base	Deploy
allenai Olmo-3-1025-7B			Base	Deploy
docling-project SmolDocling-256M-preview			Quantized	Deploy
huihui-ai Huihui-Qwen3-VL-4B-Instruct-abliterated			Fine-tuned	Deploy
p-e-w gemma-3-12b-it-heretic			Fine-tuned	Deploy
Qwen Qwen3-VL-32B-Instruct			Base	Deploy
Qwen Qwen3-VL-32B-Instruct-FP8			Quantized	Deploy
JTS-AI OpenJAI-v1.0-14B			Fine-tuned	Deploy
Qwen Qwen3Guard-Gen-8B			Fine-tuned	Deploy
Qwen Qwen3Guard-Gen-4B			Fine-tuned	Deploy
Qwen Qwen3-Omni-30B-A3B-Instruct			Base	Deploy
ibm-granite granite-docling-258M-mlx			Fine-tuned	Deploy
Qwen Qwen3-Next-80B-A3B-Instruct			Base	Deploy
NousResearch Hermes-4-14B			Fine-tuned	Deploy
XiaomiMiMo MiMo-VL-7B-RL-2508			Fine-tuned	Deploy
huihui-ai Huihui-gpt-oss-20b-BF16-abliterated			Quantized	Deploy
Qwen Qwen3-4B-Thinking-2507			Base	Deploy
huihui-ai Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated			Fine-tuned	Deploy
ibm-granite granite-guardian-3.3-8b			Base	Deploy
Qwen Qwen3-30B-A3B-Thinking-2507			Base	Deploy
Qwen Qwen3-30B-A3B-Instruct-2507			Base	Deploy
Qwen Qwen3-30B-A3B-Instruct-2507-FP8			Quantized	Deploy