20+ models
Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.
Meta's Llama 3.2 goes small with 1B and 3B models.
Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.
New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.
This model extends LLama-3 8B's context length from 8k to over 1m tokens.
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.
Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries.
SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.
This are Llama3.1 models with Anthropic's Claude Sonnet 3.5 system prompt.
Lexi Uncensored Llama3.1 8b
Vikhr-Llama3.1-8B-Instruct-R-21-09-24
https://huggingface.co/cognitivecomputations/Dolphin3.0-Llama3.1-8B-GGUF
Custom modelfile updated from llama3.1:8b into wangrongsheng/Llama3.1-8B-Chinese-Chat-Q4_0-GGUF
Quantized variants of llama3.1:8b-instruct-fp16 for the purpose of tesing in ContextAgentBench
llama.31 using cladue sonnets prompting system