mannix/
mixtral_7bx2_moe

298 1 year ago

A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI.

Models

View all →

11 models

mixtral_7bx2_moe:latest

7.3GB · 32K context window · Text · 1 year ago

mixtral_7bx2_moe:q2_K

4.8GB · 32K context window · Text · 1 year ago

mixtral_7bx2_moe:q3_K_S

5.6GB · 32K context window · Text · 1 year ago

mixtral_7bx2_moe:q3_K_M

6.2GB · 32K context window · Text · 1 year ago

mixtral_7bx2_moe:q3_K_L

6.7GB · 32K context window · Text · 1 year ago

mixtral_7bx2_moe:q4_0

7.3GB · 32K context window · Text · 1 year ago

mixtral_7bx2_moe:q4_K_S

7.3GB · 32K context window · Text · 1 year ago

mixtral_7bx2_moe:q4_K_M

7.8GB · 32K context window · Text · 1 year ago

mixtral_7bx2_moe:q5_K_S

8.9GB · 32K context window · Text · 1 year ago

mixtral_7bx2_moe:q5_K_M

9.1GB · 32K context window · Text · 1 year ago

mixtral_7bx2_moe:q6_K

11GB · 32K context window · Text · 1 year ago

Readme

The Mixtral-7Bx2 Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts.

@HuggingFace https://huggingface.co/ManniX-ITA/Mixtral_7Bx2_MoE-GGUF