Available Models

Select a model to use for chat. Models will be downloaded if not already cached.

Llama-3.2-1B-Instruct

The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.

1.2 GB

Not downloaded

Llama-3.2-3B-Instruct

The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.

2.4 GB

Not downloaded

DeepSeek-R1-Distill-Qwen-1.5B

DeepSeek-R1-Distill-Qwen-32B outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.

1.4 GB

Not downloaded

Phi-3.5-mini-instruct

The model belongs to the Phi-3 model family and supports 128K token context length.

2.1 GB

Not downloaded

SmolLM2-1.7B-Instruct

SmolLM2 is capable of solving a wide range of tasks while being lightweight enough to run on-device. This is 1.7B parameter model.

1.1 GB

Not downloaded

Qwen2.5-0.5B-Instruct

Qwen2.5 has significantly more knowledge and has greatly improved capabilities in coding and mathematics

2.0 GB

Not downloaded

Qwen2.5-Coder-1.5B-Instruct

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models.

1.3 GB

Not downloaded

Qwen2.5-Coder-3B-Instruct

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models.

2.1 GB

Not downloaded