Mistral-Small-4-119B-RotorQuant-MLX-8bit

Description

Mistral-Small-4-119B-RotorQuant-MLX-8bit is an open-weight text-generation model with roughly 119B parameters published by majentik on the Hugging Face Hub. It has 202 downloads. Runs with mlx.

Categories

• Research
• Productivity
• Design

Tags

• mistral3
• rotorquant
• kv-cache-quantization
• mistral
• moe
• sparse-moe
• multimodal
• quantized

Capabilities

• Text generation
• Conversational
• Library: mlx
• 119B parameters