Instructions to use khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled")
model = AutoModelForMultimodalLM.from_pretrained("khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled 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"
# 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",
		"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

SGLang

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

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled",
		"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 images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled",
		"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"
						}
					}
				]
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled with Docker Model Runner:
```
docker model run hf.co/khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

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}
}