Instructions to use khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-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 khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-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 khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF:Q8_0

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 khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF:Q8_0

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 khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF:Q8_0

Use Docker

docker model run hf.co/khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF:Q8_0

Ollama
How to use khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF with Ollama:
```
ollama run hf.co/khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF:Q8_0
```
Unsloth Desktop

How to use khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF:Q8_0

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": "khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF with Docker Model Runner:
```
docker model run hf.co/khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF:Q8_0
```

Lemonade

How to use khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF:Q8_0

Run and chat with the model

lemonade run user.Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-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 khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF:Q8_0

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 khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF:Q8_0

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 "khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF:Q8_0" \
  --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-Coding-Distilled

Qwen3.8-27B-Coding-Distilled is a coding- and agentic-reasoning-focused fine-tune of Qwen/Qwen3.8-27B, trained on 195M tokens of distilled reasoning traces for software-engineering and debugging tasks.

The goal of this fine-tune is to push the base model toward grounded, tool-using reasoning — reading actual files, verifying assumptions against real state, and avoiding speculative "guess-and-write" behavior — rather than producing long, free-floating chains of thought that reason about a problem without ever checking it.

⚠️ Fill in / verify before publishing: exact license inheritance from the base model, full dataset composition and sourcing, training hyperparameters, and hardware — placeholders for these are marked below.

Model Details


Base model	Qwen/Qwen3.8-27B (dense, ~27B params, Apache 2.0)
Fine-tuning method	Distillation on curated reasoning traces *(SFT / LoRA
Training data size	195M tokens
Domain focus	Coding, debugging, agentic tool-use (shell, test harnesses, CI/lint workflows)
Context length	Inherits base model context window (confirm exact value)
License	Apache 2.0 (inherited from base — confirm)
Languages	English (code + natural language)

Training Data

The model was fine-tuned on 195M tokens of reasoning traces distilled for coding and agentic-debugging scenarios. Traces emphasize:

Reading and verifying project state (files, test harnesses, CI configs) before proposing a fix
Working within existing code/output constraints instead of unnecessary rewrites
Concise, evidence-grounded reasoning over long speculative chains

Intended Use

This model is intended for:

Agentic coding assistants that need to inspect a repository before acting
Debugging and root-cause analysis tasks (e.g., CI failures, lint errors, shell script bugs)
Code review and refactoring within existing project constraints

It is not intended for use as a general-purpose chat assistant without further evaluation.

Example: Grounded vs. Speculative Reasoning

The distillation objective specifically targets the difference below, observed when comparing this fine-tune against the undistilled base model on an agentic bash-debugging task (a CI pipeline failing on a shell script with quoting bugs):

This model (fine-tuned): Immediately inspects the actual project files (test harness, target script) before forming a fix, keeping its response short and grounded in verified state rather than assumptions.
Base model: Reasons at length about what the script might contain, repeatedly acknowledges it hasn't seen the files, and ultimately proposes a fix based on guesses rather than a tool call — risking a rewrite that breaks pinned output formats the task explicitly asked to preserve.

This kind of "check before you fix" behavior is the primary signal the 195M-token distillation set was built to reinforce.

Limitations

Inherits the general limitations of the Qwen3.8-27B base model (knowledge cutoff, potential hallucination on unfamiliar codebases, no execution sandboxing on its own).
Distillation was focused on coding/agentic-debugging traces — general chat and non-coding reasoning quality has not been separately evaluated.
As with any fine-tune, behavior on out-of-distribution tasks (outside shell/CI/test-harness-style debugging) should be validated before production use.

Citation

If you use this model, please cite:

@misc{qwen38_27b_coding_distilled,
  title  = {Qwen3.8-27B-Coding-Distilled},
  author = {khazarai},
  year   = {2026},
  note   = {Fine-tune of Qwen/Qwen3.8-27B, distilled on 195M tokens of agentic coding reasoning traces},
  url    = {https://huggingface.co/khazarai/Qwen3.8-27B-Coding-Distilled}
}