Qwen3.6-27B-MTPLX-Optimized-Speed

Instructions to use finbase0530/Qwen3.6-27B-MTPLX-Optimized-Speed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use finbase0530/Qwen3.6-27B-MTPLX-Optimized-Speed with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("finbase0530/Qwen3.6-27B-MTPLX-Optimized-Speed")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

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

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

Pi new

How to use finbase0530/Qwen3.6-27B-MTPLX-Optimized-Speed with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "finbase0530/Qwen3.6-27B-MTPLX-Optimized-Speed"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "finbase0530/Qwen3.6-27B-MTPLX-Optimized-Speed"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use finbase0530/Qwen3.6-27B-MTPLX-Optimized-Speed with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "finbase0530/Qwen3.6-27B-MTPLX-Optimized-Speed"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default finbase0530/Qwen3.6-27B-MTPLX-Optimized-Speed

Run Hermes

hermes

MLX LM

How to use finbase0530/Qwen3.6-27B-MTPLX-Optimized-Speed with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "finbase0530/Qwen3.6-27B-MTPLX-Optimized-Speed"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "finbase0530/Qwen3.6-27B-MTPLX-Optimized-Speed"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "finbase0530/Qwen3.6-27B-MTPLX-Optimized-Speed",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Qwen3.6-27B-MTPLX-Optimized-Speed / MTPLX_PUBLISH_MANIFEST.json

finbase0530

Duplicate from Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed

0aa3682 18 days ago

raw

history blame contribute delete

8.19 kB

	{
	"created_at": "2026-05-03T16:59:16.607393+00:00",
	"files": [
	{
	"materialization": "clonefile",
	"name": "chat_template.jinja",
	"resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/chat_template.jinja",
	"same_inode_as_source": false,
	"size_bytes": 7764,
	"source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/chat_template.jinja"
	},
	{
	"materialization": "clonefile",
	"name": "config.json",
	"resolved_source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/config.json",
	"same_inode_as_source": false,
	"size_bytes": 5541,
	"source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/config.json"
	},
	{
	"materialization": "clonefile",
	"name": "configuration.json",
	"resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/configuration.json",
	"same_inode_as_source": false,
	"size_bytes": 51,
	"source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/configuration.json"
	},
	{
	"materialization": "clonefile",
	"name": "generation_config.json",
	"resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/generation_config.json",
	"same_inode_as_source": false,
	"size_bytes": 202,
	"source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/generation_config.json"
	},
	{
	"materialization": "clonefile",
	"name": "model-00001-of-00003.safetensors",
	"resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/model-00001-of-00003.safetensors",
	"same_inode_as_source": false,
	"size_bytes": 5343268752,
	"source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/model-00001-of-00003.safetensors"
	},
	{
	"materialization": "clonefile",
	"name": "model-00002-of-00003.safetensors",
	"resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/model-00002-of-00003.safetensors",
	"same_inode_as_source": false,
	"size_bytes": 5354185100,
	"source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/model-00002-of-00003.safetensors"
	},
	{
	"materialization": "clonefile",
	"name": "model-00003-of-00003.safetensors",
	"resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/model-00003-of-00003.safetensors",
	"same_inode_as_source": false,
	"size_bytes": 5357087747,
	"source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/model-00003-of-00003.safetensors"
	},
	{
	"materialization": "clonefile",
	"name": "model.safetensors.index.json",
	"resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/model.safetensors.index.json",
	"same_inode_as_source": false,
	"size_bytes": 218281,
	"source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/model.safetensors.index.json"
	},
	{
	"materialization": "clonefile",
	"name": "mtp.safetensors",
	"resolved_source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-CyanKiwi-Packed-BF16-INT4-v3/mtp.safetensors",
	"same_inode_as_source": false,
	"size_bytes": 337565787,
	"source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/mtp.safetensors"
	},
	{
	"materialization": "clonefile",
	"name": "mtplx_runtime.json",
	"resolved_source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/mtplx_runtime.json",
	"same_inode_as_source": false,
	"size_bytes": 2007,
	"source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/mtplx_runtime.json"
	},
	{
	"materialization": "clonefile",
	"name": "preprocessor_config.json",
	"resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/preprocessor_config.json",
	"same_inode_as_source": false,
	"size_bytes": 390,
	"source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/preprocessor_config.json"
	},
	{
	"materialization": "clonefile",
	"name": "processor_config.json",
	"resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/processor_config.json",
	"same_inode_as_source": false,
	"size_bytes": 1312,
	"source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/processor_config.json"
	},
	{
	"materialization": "clonefile",
	"name": "tokenizer.json",
	"resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/tokenizer.json",
	"same_inode_as_source": false,
	"size_bytes": 19989343,
	"source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/tokenizer.json"
	},
	{
	"materialization": "clonefile",
	"name": "tokenizer_config.json",
	"resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/tokenizer_config.json",
	"same_inode_as_source": false,
	"size_bytes": 1139,
	"source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/tokenizer_config.json"
	},
	{
	"materialization": "clonefile",
	"name": "video_preprocessor_config.json",
	"resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/video_preprocessor_config.json",
	"same_inode_as_source": false,
	"size_bytes": 385,
	"source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/video_preprocessor_config.json"
	},
	{
	"materialization": "clonefile",
	"name": "vocab.json",
	"resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/vocab.json",
	"same_inode_as_source": false,
	"size_bytes": 6722759,
	"source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/vocab.json"
	},
	{
	"materialization": "clonefile",
	"name": "LICENSE",
	"resolved_source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-CyanKiwi-Packed-BF16-INT4-v2/LICENSE",
	"same_inode_as_source": false,
	"size_bytes": 11343,
	"source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-CyanKiwi-Packed-BF16-INT4-v3/LICENSE"
	},
	{
	"materialization": "generated",
	"name": "README.md",
	"resolved_source_path": null,
	"same_inode_as_source": false,
	"size_bytes": 3041,
	"source_path": null
	},
	{
	"materialization": "generated",
	"name": "NOTICE",
	"resolved_source_path": null,
	"same_inode_as_source": false,
	"size_bytes": 460,
	"source_path": null
	}
	],
	"include_hashes": false,
	"repo_id": "Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed",
	"size_bytes": 16419071404,
	"source_provenance": {
	"base_model": "Qwen/Qwen3.6-27B",
	"base_model_revision": "6a9e13bd6fc8f0983b9b99948120bc37f49c13e9",
	"license": "Apache-2.0",
	"mtp_sidecar_revision": "8cc526ddcfdd53346f94fb9b5458ca8495a63218",
	"mtp_sidecar_source": "cyankiwi/Qwen3.6-27B-AWQ-BF16-INT4"
	},
	"source_wrapper": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP",
	"staging_dir": "/Users/youssof/Documents/MTPLX/hf-staging/Qwen3.6-27B-MTPLX-Optimized-Speed",
	"upload_policy": {
	"recommended_command_after_approval": "HF_HOME=/Users/youssof/.cache/huggingface-mtplx hf upload-large-folder Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed /Users/youssof/Documents/MTPLX/hf-staging/Qwen3.6-27B-MTPLX-Optimized-Speed --private",
	"requires_explicit_green_light": true,
	"uploaded": false
	},
	"weight_size_bytes": 16392107386
	}