README.md

metadata

license: apache-2.0
library_name: mlx
datasets:
  - DavidAU/ST-TheNextGeneration
language:
  - en
  - fr
  - zh
  - de
tags:
  - programming
  - code generation
  - code
  - codeqwen
  - moe
  - coding
  - coder
  - qwen2
  - chat
  - qwen
  - qwen-coder
  - Qwen3-Coder-30B-A3B-Instruct
  - Qwen3-30B-A3B
  - mixture of experts
  - 128 experts
  - 8 active experts
  - 1 million context
  - qwen3
  - finetune
  - brainstorm 20x
  - brainstorm
  - optional thinking
  - qwen3_moe
  - unsloth
  - mlx
base_model: DavidAU/Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG
pipeline_tag: text-generation

Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-qx64x-hi-mlx

This is a new-old-stock version of the model, with embeddings at 6 bit.

The original Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-qx64x-hi-mlx is using 4 bit embeddings

Perplexity: 4.455 ± 0.031
Peak memory: 32.84 GB

Metrics coming soon. If this proves better than the qx64-hi, it will replace it in the catalog.

-G This model Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-qx64x-hi-mlx was converted to MLX format from DavidAU/Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG using mlx-lm version 0.28.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-qx64x-hi-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)