Instructions to use ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF",
	filename="qwen3-4b-sft-fable5-glint.q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-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 ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF: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 ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF: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 ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-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": "ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF:Q4_K_M

Ollama
How to use ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF with Ollama:
```
ollama run hf.co/ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF:Q4_K_M
```

Unsloth Studio

How to use ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF 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 ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF 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 ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF to start chatting

How to use ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF: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": "ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-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 ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF: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 ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF: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 "ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF: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"

Docker Model Runner
How to use ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF with Docker Model Runner:
```
docker model run hf.co/ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF:Q4_K_M
```

Lemonade

How to use ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-4B-SFT-Fable5-Glint-GGUF-Q4_K_M

List all available models

lemonade list

Qwen3-4B-SFT-Fable5-Glint — GGUF

Quantized GGUF builds of Qwen3-4B-SFT-Fable5-Glint, a unsloth/Qwen3-4B model supervised-fine-tuned on the FABLE-5 trace corpus. These files run locally with llama.cpp, Ollama, LM Studio, and any GGUF-compatible runtime — no GPU required for the smaller quants.

Overview


Fine-tuned model	Qwen3-4B-SFT-Fable5-Glint
Base model	unsloth/Qwen3-4B
Parameter class	4B
Model family	dense
Training method	LoRA SFT (distillation)
Domain	FABLE-5 creative / agentic traces
Format	GGUF (this repo) · safetensors (merged repo)

Standard dense decoder base.

What is FABLE-5?

This model was fine-tuned on FABLE-5-Glint, a cleaned corpus of FABLE-5 pi-agent reasoning traces (each target completion may include a <think>…</think> reasoning span followed by the response). Training used assistant-only loss masking so the model learns to produce the response, not echo the prompt. The dataset is private; the fine-tuned weights are public.

Available Quantizations

File	Quant	Size	Notes
`qwen3-4b-sft-fable5-glint.q4_k_m.gguf`	Q4_K_M	~2.3 GB	Recommended — best quality/size balance
`qwen3-4b-sft-fable5-glint.q5_k_m.gguf`	Q5_K_M	~2.7 GB	Higher quality
`qwen3-4b-sft-fable5-glint.q8_0.gguf`	Q8_0	~4.0 GB	Maximum quality (near-lossless)

Which to pick: Q4_K_M is the best size/quality trade-off for most users. Use Q5_K_M if you have spare RAM/VRAM and want a little more fidelity, or Q8_0 for near-lossless output when size is not a concern.

Usage

Ollama

# Pull + run the recommended Q4_K_M quant directly from the Hub
ollama run hf.co/ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF:Q4_K_M "Write a short story about a clockwork fox."

To pin a different quant, swap the tag (e.g. :Q5_K_M, :Q8_0).

llama.cpp

# Download a single quant, then run it
huggingface-cli download ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF qwen3-4b-sft-fable5-glint.q4_k_m.gguf --local-dir .
llama-cli -m qwen3-4b-sft-fable5-glint.q4_k_m.gguf -p "Write a short story about a clockwork fox." -n 512

# Or serve an OpenAI-compatible endpoint
llama-server -m qwen3-4b-sft-fable5-glint.q4_k_m.gguf --host 0.0.0.0 --port 8080

LM Studio

Search for ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF in LM Studio, or download a .gguf above and load it from disk.

Python (llama-cpp-python)

from llama_cpp import Llama
llm = Llama.from_pretrained(repo_id="ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF", filename="*q4_k_m.gguf", n_ctx=4096)
out = llm.create_chat_completion(
    messages=[{"role": "user", "content": "Write a short story about a clockwork fox."}]
)
print(out["choices"][0]["message"]["content"])

Prompt format

Use the base model's chat template (applied automatically by Ollama / LM Studio / create_chat_completion). The model was trained on 2-turn user → assistant chats. For thinking-style bases, the model may emit a <think>…</think> span before its answer.

Training details

Hyperparameter	Value
Method	LoRA SFT, merged to 16-bit then quantized
LoRA rank / α	16 / 16
Learning rate	0.0002
LR scheduler	cosine (warmup 0.03)
Max sequence length	4096
Epochs	3
Loss masking	assistant-only
Quantization toolchain	llama.cpp `convert_hf_to_gguf` + `llama-quantize`

A deterministic ~5% slice of the corpus was held out from training for evaluation.

Intended use & limitations

Intended: local/offline creative writing, reasoning-trace style generation, and experimentation with FABLE-5-distilled behavior on consumer hardware.
Limitations: inherits the base model's knowledge cutoff and biases; quantization (especially Q4_K_M) trades some fidelity for size; not safety-tuned for production use without additional guardrails. Outputs may be fictional/unverified.

Citation

@misc{azarkhalili2026qwen34bsftfable5glint,
    author = {Azarkhalili, Behrooz},
    title  = {Qwen3-4B-SFT-Fable5-Glint: FABLE-5 SFT distillation (GGUF)},
    year   = {2026},
    publisher = {Hugging Face},
    url    = {https://huggingface.co/ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF}
}

Downloads last month: 391

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

5-bit

8-bit

Model tree for ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint-GGUF

Base model

ermiaazarkhalili/Qwen3-4B-SFT-Fable5-Glint

Quantized

(1)

this model