Leanstral-TurboQuant-MLX-2bit

Description

Leanstral-TurboQuant-MLX-2bit is an open-weight text-generation model with roughly 2B parameters published by majentik on the Hugging Face Hub. It has 465 downloads. Runs with mlx.

Categories

• Writing

Tags

• mistral3
• turboquant
• kv-cache-quantization
• 2-bit
• weight-quantization
• leanstral
• lean4
• formal-proofs

Capabilities

• Text generation
• Library: mlx
• 2B parameters