The current, most capable model that runs on a single GPU.
28.4M Pulls 29 Tags Updated 1 week ago
Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B.
11.5M Pulls 94 Tags Updated 1 year ago
Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1
5.6M Pulls 102 Tags Updated 1 year ago
Gemma 3n models are designed for efficient execution on everyday devices such as laptops, tablets or phones.
913.4K Pulls 9 Tags Updated 5 months ago
FunctionGemma is a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.
893 Pulls 4 Tags Updated yesterday
CodeGemma is a collection of powerful, lightweight models that can perform a variety of coding tasks like fill-in-the-middle code completion, code generation, natural language understanding, mathematical reasoning, and instruction following.
1.7M Pulls 85 Tags Updated 1 year ago
EmbeddingGemma is a 300M parameter embedding model from Google.
328.3K Pulls 5 Tags Updated 3 months ago
ShieldGemma is set of instruction tuned models for evaluating the safety of text prompt input and text output responses against a set of defined safety policies.
83.9K Pulls 49 Tags Updated 1 year ago
Google's most intelligent model with SOTA reasoning and multimodal understanding, and powerful agentic and vibe coding capabilities.
38.4K Pulls 1 Tag Updated 1 month ago
The IBM Granite Embedding 30M and 278M models models are text-only dense biencoder embedding models, with 30M available in English only and 278M serving multilingual use cases.
144.2K Pulls 6 Tags Updated 1 year ago
A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
561.4K Pulls 5 Tags Updated 9 months ago
Dolphin 3.0 Llama 3.1 8B 🐬 is the next generation of the Dolphin series of instruct-tuned models designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.
3.5M Pulls 5 Tags Updated 11 months ago
Mistral Large 2 is Mistral's new flagship model that is significantly more capable in code generation, mathematics, and reasoning with 128k context window and support for dozens of languages.
298.9K Pulls 32 Tags Updated 1 year ago
General use models based on Llama and Llama 2 from Nous Research.
248.3K Pulls 63 Tags Updated 2 years ago
General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.
230.4K Pulls 111 Tags Updated 2 years ago
A strong multi-lingual general language model with competitive performance to Llama 3.
191.1K Pulls 32 Tags Updated 1 year ago
Code generation model based on Code Llama.
125.1K Pulls 49 Tags Updated 1 year ago
General use model based on Llama 2.
81.4K Pulls 73 Tags Updated 2 years ago
Great code generation model based on Llama2.
77.1K Pulls 19 Tags Updated 2 years ago
The IBM Granite 1B and 3B models are long-context mixture of experts (MoE) Granite models from IBM designed for low latency usage.
1.6M Pulls 33 Tags Updated 11 months ago