Prophet25200
/

petspeak-mlx-q4

4-bit precision

Model card Files Files and versions

PetSpeak Q4_K_M — Llama-3-8B finetuné

Built with Meta Llama 3.

Llama-3-8B-Instruct finetuné via LoRA, quantifié Q4_K_M pour Apple MLX. Utilisé par l'app iOS PetMind.

Downloads last month: 3

Safetensors

Model size

1B params

Tensor type

F16

·

U32

·

MLX

Hardware compatibility

Log In to add your hardware

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Prophet25200/petspeak-mlx-q4

Base model

meta-llama/Meta-Llama-3-8B-Instruct

Adapter

(1175)

this model