README.md

metadata

license: apache-2.0
base_model: DavidAU/Qwen3-MOE-6x6B-Star-Trek-Universe-Alpha-D-256k-ctx-36B
datasets:
  - DavidAU/horror-nightmare1
  - DavidAU/ST-Org
  - DavidAU/ST-TNG
  - DavidAU/ST-DS9
  - DavidAU/ST-VOY
  - DavidAU/ST-ENT
  - DavidAU/ST-DIS
language:
  - en
pipeline_tag: text-generation
tags:
  - programming
  - code generation
  - code
  - coding
  - coder
  - chat
  - brainstorm
  - qwen
  - qwen3
  - qwencoder
  - brainstorm 20x
  - creative
  - all uses cases
  - Jan-V1
  - horror
  - science fiction
  - fantasy
  - Star Trek
  - Star Trek Original
  - Star Trek The Next Generation
  - Star Trek Deep Space Nine
  - Star Trek Voyager
  - Star Trek Enterprise
  - Star Trek Discovery.
  - finetune
  - thinking
  - reasoning
  - unsloth
  - 6x6B
  - moe
  - mixture of experts
  - mlx
library_name: mlx

Qwen3-MOE-6x6B-Star-Trek-Universe-Alpha-D-256k-ctx-36B-qx86-hi-mlx

This model Qwen3-MOE-6x6B-Star-Trek-Universe-Alpha-D-256k-ctx-36B-qx86-hi-mlx was converted to MLX format from DavidAU/Qwen3-MOE-6x6B-Star-Trek-Universe-Alpha-D-256k-ctx-36B using mlx-lm version 0.28.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Qwen3-MOE-6x6B-Star-Trek-Universe-Alpha-D-256k-ctx-36B-qx86-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)