Instructions to use Mia-AiLab/Qwable-3.6-27b-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mia-AiLab/Qwable-3.6-27b-MTP with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Mia-AiLab/Qwable-3.6-27b-MTP", dtype="auto")

llama-cpp-python

How to use Mia-AiLab/Qwable-3.6-27b-MTP with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Mia-AiLab/Qwable-3.6-27b-MTP",
	filename="Qwable-3.6-27b_f16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Mia-AiLab/Qwable-3.6-27b-MTP with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Mia-AiLab/Qwable-3.6-27b-MTP:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Mia-AiLab/Qwable-3.6-27b-MTP:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Mia-AiLab/Qwable-3.6-27b-MTP:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Mia-AiLab/Qwable-3.6-27b-MTP:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Mia-AiLab/Qwable-3.6-27b-MTP:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Mia-AiLab/Qwable-3.6-27b-MTP:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Mia-AiLab/Qwable-3.6-27b-MTP:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Mia-AiLab/Qwable-3.6-27b-MTP:Q4_K_M

Use Docker

docker model run hf.co/Mia-AiLab/Qwable-3.6-27b-MTP:Q4_K_M

LM Studio
Jan
Ollama
How to use Mia-AiLab/Qwable-3.6-27b-MTP with Ollama:
```
ollama run hf.co/Mia-AiLab/Qwable-3.6-27b-MTP:Q4_K_M
```

Unsloth Studio

How to use Mia-AiLab/Qwable-3.6-27b-MTP with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Mia-AiLab/Qwable-3.6-27b-MTP to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Mia-AiLab/Qwable-3.6-27b-MTP to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Mia-AiLab/Qwable-3.6-27b-MTP to start chatting

How to use Mia-AiLab/Qwable-3.6-27b-MTP with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Mia-AiLab/Qwable-3.6-27b-MTP:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Mia-AiLab/Qwable-3.6-27b-MTP:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Mia-AiLab/Qwable-3.6-27b-MTP with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Mia-AiLab/Qwable-3.6-27b-MTP:Q4_K_M

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 Mia-AiLab/Qwable-3.6-27b-MTP:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Mia-AiLab/Qwable-3.6-27b-MTP with Docker Model Runner:
```
docker model run hf.co/Mia-AiLab/Qwable-3.6-27b-MTP:Q4_K_M
```

Lemonade

How to use Mia-AiLab/Qwable-3.6-27b-MTP with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Mia-AiLab/Qwable-3.6-27b-MTP:Q4_K_M

Run and chat with the model

lemonade run user.Qwable-3.6-27b-MTP-Q4_K_M

List all available models

lemonade list

no support llama cpp and lm studio

by xueqing12 - opened 4 days ago

Discussion

xueqing12

4 days ago

llama cpp
load_tensors: loading model tensors, this can take a while... (mmap = true, direct_io = false)
llama_model_load: error loading model: missing tensor 'blk.64.attn_norm.weight'
[0mllama_model_load_from_file_impl: failed to load model
[0mcommon_init_from_params: failed to load model 'Qwable-3.6-27b_q6_k.gguf'
[0msrv load_model: failed to load model, 'Qwable-3.6-27b_q6_k.gguf'
[0msrv operator (): operator (): cleaning up before exit...
main: exiting due to model loading error

lm studio
Engine protocol runtime llama-server for 3uVoa7nZFFRn3PDfwFGQTxh4 exited before becoming healthy. exitCode=1, signal=null

Mia-AiLab

Owner 4 days ago

Hey there! I am aware, will be fixed today!

Mia-AiLab

Owner 4 days ago

retry pls

fb700

2 days ago

全网唯一支持MTP+TurboQuant并解决视觉推理崩溃的分支，比官方最新版本mtp快25%
https://github.com/BoFan-tunning/llama.cpp-MTP-TurboQuant

MyHumbleUsername

about 16 hours ago

retry pls

I'm not sure if this issues are connected. But when I'm running this model in LM Studio and trying to use it in connection to Claude CLI or OpenClaude, I'm getting this error:

[INFO]
[qwable-3.6-27b-mtp] Running Anthropic messages API on conversation with 3 messages.
[ERROR]
[Server Error] {
"type": "error",
"error": {
"type": "api_error",
"message": "Engine protocol predict request returned 400: {"error":{"code":400,"message":"Unable to generate parser for this template. Automatic parser generation failed: \n------------\nWhile executing CallExpression at line 85, column 32 in source:\n...first %}↵ {{- raise_exception('System message must be at the beginnin...\n ^\nError: Jinja Exception: System message must be at the beginning.","type":"invalid_request_error"}}"
}
}

Could you please tell me what is the issue here? Because when I'm using the base Qwen3.6-27B-MTP it works like a charm

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment