Instructions to use unsloth/Qwen3.8-27B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use unsloth/Qwen3.8-27B-GGUF 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 unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
llama cli -hf unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
llama cli -hf unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M

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 unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M

Use Docker

docker model run hf.co/unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use unsloth/Qwen3.8-27B-GGUF with Ollama:
```
ollama run hf.co/unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M
```
Unsloth Desktop

How to use unsloth/Qwen3.8-27B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M

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:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use unsloth/Qwen3.8-27B-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M
```

Lemonade

How to use unsloth/Qwen3.8-27B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.8-27B-GGUF-UD-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use unsloth/Qwen3.8-27B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/Qwen3.8-27B-GGUF:UD-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 unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use unsloth/Qwen3.8-27B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M

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://127.0.0.1:8080/v1 \
  --custom-model-id "unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M" \
  --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"

Can i ask the sweet point for 12gb cards?

#81

by AsThirtyThree - opened Aug 19

Discussion

AsThirtyThree

Aug 19

i researched a lot but i cant able to find a sweet point for my 12gb card,is iq2s good?or q2k xl makes a big difference?or if unsloth upload non mtp files and reduces iq3xxs model size i will try iq3xxs as well,an additional mtp layer(400-500mb) just slows model in my situation

renatomoselli

Aug 19

I'm using beellama.cpp with "kv cache = kvarn4" and "tail = 1024", you could even use kvarn3 and kvarn2, this greatly reduces the quality loss in the cache in comparison with default quants

AsThirtyThree

Aug 19

I'm using beellama.cpp with "kv cache = kvarn4" and "tail = 1024", you could even use kvarn3 and kvarn2, this greatly reduces the quality loss in the cache in comparison with default quants

thanks✅✅

puchuu

Aug 22

•

edited Aug 22

The best solution will be actually to buy a same second card and set the split mode to tensor. Use of single 12gb card today will be a waste of electricity: you will need to use extreme quants, quantized kv cache (or cpu only kv cache).

AsThirtyThree

Aug 22

The best solution will be actually to buy a same second card and set the split mode to tensor. Use of single 12gb card today will be a waste of electricity: you will need to use extreme quants, quantized kv cache (or cpu only kv cache).

yeah i know but i cant buy a new gpu,im just hoping for 35b a3b version(3.6 35b a3b just gives 53 token per second with 64k context on my machine)

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