Filter by
(1)
Distilled LLaMA by DeepSeek, fast and optimized for real-world tasks
1y
100K+
79
mxbai-embed-large-v1 is a top English embed model by Mixedbread AI, great for RAG and more.
1y
10K+
3
SmolLM3 is a 3.1B model for efficient on-device use, with strong performance in chat
1y
100K+
9
Gemma 4: multimodal open AI models by Google, optimized for reasoning, coding, and long context.
7m
50K+
Newest LLama 3 release with improved reasoning and generation quality
1y
100K+
21
24B multimodal instruction model by Mistral AI, tuned for accuracy, tool use & fewer repeats
1y
10K+
1
Kimi K2 Thinking: open-source agent with deep reasoning, stable tool use, fast INT4, 256k context.
11m
50K+
4
Image generation model, uses a base latent diffusion model plus a refiner.
9m
50K+
8
Google’s latest Gemma, in its QAT (quantization aware trained) variant
1y
100K+
23
Ministral 3: compact vision-enabled model with near-24B performance, optimized for local edge use
11m
50K+
4
Granite Docling is a multimodal model for efficient document conversion.
1y
50K+
2
1T MoE multimodal agentic model with long-horizon coding, swarm orchestration, and native vision
6m
50K+
1
Granite Embedding Multilingual is a 278 million parameter, encoder‑only XLM‑RoBERTa‑style
1y
50K+
4
FunctionGemma is a 270M open model for fine-tuned, offline function-calling agents on small devices.
10m
10K+
1
