Mistral models quantized to run with MLX
Luis Catacora
lucataco
AI & ML interests
Generative AI, Stable Diffusion, Faceswap, MoE LLMs
Organizations
Collections
2
models
26
lucataco/Phi-3-mini-4k-instruct-openassistant
Text Generation
•
Updated
lucataco/dolphin-2.9-llama3-70b-8bit
Updated
•
1
lucataco/Llama-3-8B-16K-8bit
Updated
•
6
lucataco/Llama-3-8B-16K
Text Generation
•
Updated
•
6
lucataco/Llama-3-8B-16K-4bit
Updated
•
2
lucataco/Mixtral-8x22B-Instruct-v0.1-4bit
Updated
•
1
lucataco/Mixtral-8x22B-v0.1-4bit
Updated
•
1
lucataco/Meta-Llama-3-70B-4bit
Text Generation
•
Updated
•
7
lucataco/Meta-Llama-3-70B-Instruct-4bit
Text Generation
•
Updated
•
2
lucataco/Meta-Llama-3-8B-Instruct-4bit
Text Generation
•
Updated
•
3