README.md

metadata

license: apache-2.0
base_model: DavidAU/Mistral-Devstral-2505-CODER-Brainstorm20x-34B
language:
  - en
  - fr
  - de
  - es
  - pt
  - it
  - ja
  - ko
  - ru
  - zh
  - ar
  - fa
  - id
  - ms
  - ne
  - pl
  - ro
  - sr
  - sv
  - tr
  - uk
  - vi
  - hi
  - bn
pipeline_tag: text-generation
tags:
  - merge
  - programming
  - code generation
  - code
  - coding
  - coder
  - chat
  - brainstorm
  - brainstorm20x
  - mistral
  - mlx
library_name: mlx

Mistral-Devstral-2505-CODER-Brainstorm20x-34B-q8-mlx

This model Mistral-Devstral-2505-CODER-Brainstorm20x-34B-q8-mlx was converted to MLX format from DavidAU/Mistral-Devstral-2505-CODER-Brainstorm20x-34B using mlx-lm version 0.26.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Mistral-Devstral-2505-CODER-Brainstorm20x-34B-q8-mlx")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)