lam · Ollama

llama3-gradient

This model extends LLama-3 8B's context length from 8k to over 1m tokens.

628.8K Pulls 35 Tags Updated 1 year ago

lfm2

LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion parameters while keeping inference efficient.

tools 24b

987.6K Pulls 6 Tags Updated 4 weeks ago

llama3.1

Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.

tools 8b 70b 405b

111.9M Pulls 93 Tags Updated 1 year ago

llama3.3

New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.

tools 70b

3.5M Pulls 14 Tags Updated 1 year ago

qwen3-coder-next

Qwen3-Coder-Next is a coding-focused language model from Alibaba's Qwen team, optimized for agentic coding workflows and local development.

tools cloud

901.5K Pulls 4 Tags Updated 1 month ago

lfm2.5-thinking

LFM2.5 is a new family of hybrid models designed for on-device deployment.

tools 1.2b

1M Pulls 5 Tags Updated 2 months ago

qwen3-vl

The most powerful vision-language model in the Qwen model family to date.

vision tools thinking cloud 2b 4b 8b 30b 32b 235b

2.4M Pulls 59 Tags Updated 4 months ago

minimax-m2.5

MiniMax-M2.5 is a state-of-the-art large language model designed for real-world productivity and coding tasks.

cloud

142.9K Pulls 1 Tag Updated 1 month ago

olmo-3

Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.

7b 32b

280.6K Pulls 15 Tags Updated 3 months ago

deepseek-ocr

DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.

vision 3b

356.8K Pulls 3 Tags Updated 4 months ago

olmo-3.1

Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.

tools 32b

176.1K Pulls 10 Tags Updated 3 months ago

minimax-m2

MiniMax M2 is a high-efficiency large language model built for coding and agentic workflows.

cloud

88K Pulls 1 Tag Updated 4 months ago

mistral-large-3

A general-purpose multimodal mixture-of-experts model for production-grade tasks and enterprise workloads.

cloud

31.5K Pulls 1 Tag Updated 3 months ago

qwen3

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

tools thinking 0.6b 1.7b 4b 8b 14b 30b 32b 235b

24.8M Pulls 58 Tags Updated 5 months ago

qwen2.5vl

Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.

vision 3b 7b 32b 72b

1.5M Pulls 17 Tags Updated 10 months ago

phi4-reasoning

Phi 4 reasoning and reasoning plus are 14-billion parameter open-weight reasoning models that rival much larger models on complex reasoning tasks.

14b

1.3M Pulls 9 Tags Updated 10 months ago

llama4

Meta's latest collection of multimodal models.

vision tools 16x17b 128x17b

1.4M Pulls 11 Tags Updated 9 months ago

granite3.3

IBM Granite 2B and 8B models are 128K context length language models that have been fine-tuned for improved reasoning and instruction-following capabilities.

tools 2b 8b

950.3K Pulls 3 Tags Updated 11 months ago

kimi-k2

A state-of-the-art mixture-of-experts (MoE) language model. Kimi K2-Instruct-0905 demonstrates significant improvements in performance on public benchmarks and real-world coding agent tasks.

cloud

50.5K Pulls 1 Tag Updated 5 months ago

llama3.2

Meta's Llama 3.2 goes small with 1B and 3B models.

tools 1b 3b

62.2M Pulls 63 Tags Updated 1 year ago