Instructions to use jajmangold/Qwen3.8-27B-MTP-TQ3_4S with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use jajmangold/Qwen3.8-27B-MTP-TQ3_4S with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf jajmangold/Qwen3.8-27B-MTP-TQ3_4S # Run inference directly in the terminal: llama cli -hf jajmangold/Qwen3.8-27B-MTP-TQ3_4S
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf jajmangold/Qwen3.8-27B-MTP-TQ3_4S # Run inference directly in the terminal: llama cli -hf jajmangold/Qwen3.8-27B-MTP-TQ3_4S
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf jajmangold/Qwen3.8-27B-MTP-TQ3_4S # Run inference directly in the terminal: ./build/bin/llama cli -hf jajmangold/Qwen3.8-27B-MTP-TQ3_4S
Use Docker
docker model run hf.co/jajmangold/Qwen3.8-27B-MTP-TQ3_4S
- Llama new
- LM Studio
- Jan
- vLLM
How to use jajmangold/Qwen3.8-27B-MTP-TQ3_4S with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jajmangold/Qwen3.8-27B-MTP-TQ3_4S" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jajmangold/Qwen3.8-27B-MTP-TQ3_4S", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/jajmangold/Qwen3.8-27B-MTP-TQ3_4S
- Ollama
How to use jajmangold/Qwen3.8-27B-MTP-TQ3_4S with Ollama:
ollama run hf.co/jajmangold/Qwen3.8-27B-MTP-TQ3_4S
- Unsloth Desktop
- Pi
How to use jajmangold/Qwen3.8-27B-MTP-TQ3_4S with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf jajmangold/Qwen3.8-27B-MTP-TQ3_4S
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "jajmangold/Qwen3.8-27B-MTP-TQ3_4S" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use jajmangold/Qwen3.8-27B-MTP-TQ3_4S with Docker Model Runner:
docker model run hf.co/jajmangold/Qwen3.8-27B-MTP-TQ3_4S
- Lemonade
How to use jajmangold/Qwen3.8-27B-MTP-TQ3_4S with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull jajmangold/Qwen3.8-27B-MTP-TQ3_4S
Run and chat with the model
lemonade run user.Qwen3.8-27B-MTP-TQ3_4S-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use jajmangold/Qwen3.8-27B-MTP-TQ3_4S with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf jajmangold/Qwen3.8-27B-MTP-TQ3_4S
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://127.0.0.1:9931/v1 hermes config set model.default jajmangold/Qwen3.8-27B-MTP-TQ3_4S
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use jajmangold/Qwen3.8-27B-MTP-TQ3_4S with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf jajmangold/Qwen3.8-27B-MTP-TQ3_4S
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "jajmangold/Qwen3.8-27B-MTP-TQ3_4S" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Qwen3.8-27B-MTP-TQ3_4S
TurboQuant TQ3_4S GGUF build of Qwen/Qwen3.8-27B with native MTP (Multi-Token Prediction) draft heads for speculative decoding.
This file was quantized with the TurboQuant toolchain and is intended for the public TurboQuant runtime fork maintained by Y Tan (GitHub: turbo-tan):
- Runtime fork: https://github.com/turbo-tan/llama.cpp-tq3
- Reference releases by Y Tan: https://huggingface.co/YTan2000
Credit goes to Y Tan for the TQ3_4S quantization path and the llama.cpp runtime support this model depends on. See the Qwen3.5-27B-TQ3_4S reference card for the format's published quality and speed characteristics.
Required Runtime
This model requires the TurboQuant runtime fork โ stock llama.cpp builds cannot load the TQ3_4S tensor type.
This is an MTP model: the GGUF includes the trained MTP draft block, so serve it with draft-MTP speculative decoding for full decode speed.
git clone https://github.com/turbo-tan/llama.cpp-tq3.git
cd llama.cpp-tq3
cmake -B build -DGGML_CUDA=ON -DCMAKE_BUILD_TYPE=Release
cmake --build build -j
File
- File:
Qwen3.8-27B-MTP-TQ3_4S.gguf - Size: 13.68 GB (12.74 GiB)
- SHA256:
b734f643665a9d1f356cfcca0ef65572eb08ab9ab25c29b1ddf4ac602548e2cb - Quantization:
TQ3_4S(3.5-bit Walsh-Hadamard transform format) - Architecture:
qwen35โ 64 layers, hybrid Gated DeltaNet + Gated Attention, 1 MTP draft block - Context: 262,144 tokens native
Recommended Launch
./build/bin/llama-server \
-m Qwen3.8-27B-MTP-TQ3_4S.gguf \
--host 127.0.0.1 --port 8080 \
-c 32768 -np 1 -ngl 99 -fa on \
-ctk q8_0 -ctv tq3_0 \
--spec-type draft-mtp \
--spec-draft-n-min 1 \
--spec-draft-n-max 2 \
--spec-draft-p-min 0.0 \
--no-spec-draft-backend-sampling \
--reasoning off --jinja
Settings notes:
--spec-draft-n-max 2is optimal for the 3.8 MTP head (measured)--no-spec-draft-backend-samplingkeeps CUDA graph reuse high- The model supports thinking mode via
--reasoning-format deepseek --reasoning-budget N
License
Subject to the Qwen3.8-27B base model license (Apache 2.0) and the license terms of the runtime components used to run the GGUF.
- Downloads last month
- 16
We're not able to determine the quantization variants.
Model tree for jajmangold/Qwen3.8-27B-MTP-TQ3_4S
Base model
Qwen/Qwen3.8-27B