Instructions to use Ebumping/Qwen3-32B-Fable-Distill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ebumping/Qwen3-32B-Fable-Distill with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen3-32b-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "Ebumping/Qwen3-32B-Fable-Distill")

Transformers

How to use Ebumping/Qwen3-32B-Fable-Distill with Transformers:

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

pipe = pipeline("text-generation", model="Ebumping/Qwen3-32B-Fable-Distill")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Ebumping/Qwen3-32B-Fable-Distill")
model = AutoModelForMultimodalLM.from_pretrained("Ebumping/Qwen3-32B-Fable-Distill")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use Ebumping/Qwen3-32B-Fable-Distill with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Ebumping/Qwen3-32B-Fable-Distill",
	filename="Qwen3-32B-Fable-Distill.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 Ebumping/Qwen3-32B-Fable-Distill with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Ebumping/Qwen3-32B-Fable-Distill:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Ebumping/Qwen3-32B-Fable-Distill:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Ebumping/Qwen3-32B-Fable-Distill:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Ebumping/Qwen3-32B-Fable-Distill: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 Ebumping/Qwen3-32B-Fable-Distill:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Ebumping/Qwen3-32B-Fable-Distill: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 Ebumping/Qwen3-32B-Fable-Distill:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ebumping/Qwen3-32B-Fable-Distill:Q4_K_M

Use Docker

docker model run hf.co/Ebumping/Qwen3-32B-Fable-Distill:Q4_K_M

LM Studio
Jan

vLLM

How to use Ebumping/Qwen3-32B-Fable-Distill with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ebumping/Qwen3-32B-Fable-Distill"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ebumping/Qwen3-32B-Fable-Distill",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ebumping/Qwen3-32B-Fable-Distill:Q4_K_M

SGLang

How to use Ebumping/Qwen3-32B-Fable-Distill 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 "Ebumping/Qwen3-32B-Fable-Distill" \
    --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": "Ebumping/Qwen3-32B-Fable-Distill",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Ebumping/Qwen3-32B-Fable-Distill" \
        --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": "Ebumping/Qwen3-32B-Fable-Distill",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Ebumping/Qwen3-32B-Fable-Distill with Ollama:
```
ollama run hf.co/Ebumping/Qwen3-32B-Fable-Distill:Q4_K_M
```

Unsloth Studio

How to use Ebumping/Qwen3-32B-Fable-Distill 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 Ebumping/Qwen3-32B-Fable-Distill 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 Ebumping/Qwen3-32B-Fable-Distill to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ebumping/Qwen3-32B-Fable-Distill to start chatting

How to use Ebumping/Qwen3-32B-Fable-Distill with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Ebumping/Qwen3-32B-Fable-Distill: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": "Ebumping/Qwen3-32B-Fable-Distill:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Ebumping/Qwen3-32B-Fable-Distill with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Ebumping/Qwen3-32B-Fable-Distill: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 Ebumping/Qwen3-32B-Fable-Distill:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Ebumping/Qwen3-32B-Fable-Distill with Docker Model Runner:
```
docker model run hf.co/Ebumping/Qwen3-32B-Fable-Distill:Q4_K_M
```

Lemonade

How to use Ebumping/Qwen3-32B-Fable-Distill with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ebumping/Qwen3-32B-Fable-Distill:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-32B-Fable-Distill-Q4_K_M

List all available models

lemonade list

Qwen3-32B-Fable-Distill (v0.2)

A Qwen3-32B model fine-tuned via SFT on curated reasoning traces distilled from frontier models.

What is New in v0.2

Proper reasoning separation - blocks preserved as distinct reasoning traces (v0.1 had reasoning flattened into generation)
Assistant-only loss - training loss computed only on assistant tokens
4,207 training examples - CoT-less examples dropped, Claude channel converted to Qwen3 format
789 training steps, LoRA rank 64, Qwen3-32B 4-bit base

Training Details

Parameter	Value
Base model	unsloth/qwen3-32b-bnb-4bit
Method	SFT via TRL
LoRA rank	64
Training steps	789
Dataset size	4,207 examples
Loss masking	Assistant-only
Precision	BF16 (merged weights)

Framework Versions

PEFT 0.19.1
TRL 0.24.0
Transformers 5.5.0
PyTorch 2.10.0
Datasets 4.3.0
Tokenizers 0.22.2

Quick Start

LoRA adapter (recommended)

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("unsloth/qwen3-32b-bnb-4bit")
model = PeftModel.from_pretrained(base, "Ebumping/Qwen3-32B-Fable-Distill")
tokenizer = AutoTokenizer.from_pretrained("Ebumping/Qwen3-32B-Fable-Distill")

Merged BF16 weights

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("Ebumping/Qwen3-32B-Fable-Distill")
tokenizer = AutoTokenizer.from_pretrained("Ebumping/Qwen3-32B-Fable-Distill")

GGUF (llama.cpp / Ollama)

llama-server -hf Ebumping/Qwen3-32B-Fable-Distill:Q4_K_M
ollama run hf.co/Ebumping/Qwen3-32B-Fable-Distill:Q4_K_M

vLLM

vllm serve "Ebumping/Qwen3-32B-Fable-Distill"

VRAM Requirements

Format	Size	Min VRAM
BF16 merged	~64 GB	80 GB+
Q8_0 GGUF	~33 GB	40 GB+
Q5_K_M GGUF	~23 GB	28 GB+
Q4_K_M GGUF	~20 GB	24 GB
Q3_K_M GGUF	~16 GB	20 GB+

Version History

v0.2 (current) - Reasoning properly separated with traces, assistant-only loss, 4,207 examples
v0.1 - Reasoning flattened into generation

Citation

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouedec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {url{https://github.com/huggingface/trl}}
}

Downloads last month: 275

Safetensors

Model size

33B params

Tensor type

BF16