Instructions to use AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-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 AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-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 AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-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 AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-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 AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-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 AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF:Q4_K_M

Use Docker

docker model run hf.co/AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-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": "AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF:Q4_K_M

Ollama
How to use AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF with Ollama:
```
ollama run hf.co/AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF:Q4_K_M
```
Unsloth Desktop

How to use AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF: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": "AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF with Docker Model Runner:
```
docker model run hf.co/AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF:Q4_K_M
```

Lemonade

How to use AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Parable-SmolLM3-3B-Claude-Fable-5-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-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 AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-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 AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-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 "AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-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"

Parable-SmolLM3-3B-Claude-Fable-5-GGUF / README.md

AnkitAI

Upload folder using huggingface_hub

fe20e86 verified 2 months ago

preview code

Raw History Blame

4.46 kB

	---
	license: apache-2.0
	base_model: HuggingFaceTB/SmolLM3-3B
	datasets:
	- Glint-Research/Fable-5-traces
	- Roman1111111/gpt5.5-terminal
	pipeline_tag: text-generation
	library_name: llama.cpp
	tags:
	- gguf
	- qlora
	- agentic
	- coding
	- reasoning
	- smollm3
	---

	# Parable-SmolLM3-3B-Claude-Fable-5-GGUF

	![SmolLM3-3B](banner.svg)

	Part of the Parable series: small local LLMs fine-tuned on genuine agent
	traces. This is HuggingFaceTB/SmolLM3-3B tuned on real Claude Fable 5 agent
	transcripts so its step-by-step reasoning voice carries into local use.

	Full-precision weights: [Parable-SmolLM3-3B-Claude-Fable-5](https://huggingface.co/AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5)

	## Files

	\| File \| Quant \| Size \| \|
	\|---\|---\|---\|---\|
	\| Parable-SmolLM3-3B-Claude-Fable-5-GGUF-Q4_K_M.gguf \| Q4_K_M \| 1.9 GB \| recommended default \|
	\| Parable-SmolLM3-3B-Claude-Fable-5-GGUF-Q5_K_M.gguf \| Q5_K_M \| 2.2 GB \| \|
	\| Parable-SmolLM3-3B-Claude-Fable-5-GGUF-Q6_K.gguf \| Q6_K \| 2.5 GB \| \|
	\| Parable-SmolLM3-3B-Claude-Fable-5-GGUF-Q8_0.gguf \| Q8_0 \| 3.3 GB \| \|
	\| Parable-SmolLM3-3B-Claude-Fable-5-GGUF-F16.gguf \| F16 \| 6.2 GB \| for re-quantizing \|

	## Usage

	```bash
	llama-cli -m Parable-SmolLM3-3B-Claude-Fable-5-GGUF-Q4_K_M.gguf \
	-c 4096 -p "Write a python function that reverses a string." --temp 0.6
	```

	SmolLM3 is supported by current llama.cpp releases (brew, Ollama, LM Studio
	builds included); no special build is required.

	Output begins with a `<think>...</think>` reasoning block, then the answer.
	If you are building on top of this model, parse and strip the think block
	before showing text to end users. The chat template identifies the model as
	"Parable, a coding assistant that reasons before it answers."

	## Model details

	- Base: [HuggingFaceTB/SmolLM3-3B](https://huggingface.co/HuggingFaceTB/SmolLM3-3B) (3B, Apache-2.0, 64k context)
	- Method: MLX QLoRA on a 4-bit quantized base, 16 layers adapted,
	6.7M trainable parameters (0.218%)
	- Data: 4,076 training rows from real Claude Fable 5 agent-session
	traces plus gpt5.5-terminal transcripts, prepared at a 4,096-token window
	(268 over-length rows dropped; 226/226 rows held out for validation/test)
	- Schedule: 1,200-iteration budget across a paused-and-resumed run;
	best checkpoint selected on validation loss (iteration 200 of the final
	segment, val 1.154)

	## Evaluation

	\| \| Held-out trace test loss \|
	\|---\|---\|
	\| SmolLM3-3B base \| 1.889 \|
	\| This model \| 1.115 \|

	The tuned model fits the Fable-5 reasoning distribution 41% better by
	held-out loss on a 226-row test split never seen in training. That is the
	honest headline for what this fine-tune does; we do not claim general
	benchmark gains.

	This lane trains on trace data without a replay mix, so impact on general
	coding benchmarks is unmeasured here. The series' technical report
	(DOI: [10.5281/zenodo.21676407](https://doi.org/10.5281/zenodo.21676407))
	documents why that matters and what replay does about it.

	## Limitations

	- Training ran on a 4-bit quantized base (16 GB M1 constraint); the F16
	merge and higher quants cannot exceed 4-bit-base quality.
	- Modest scale: one seed, loss-based evaluation, no external benchmark run
	for this model yet.
	- Not trained for: multi-file repo navigation, vision, non-English.
	- Inherits SmolLM3-3B's knowledge cutoff. Treat generated commands as
	drafts to review.

	## Quantization

	Quantized with llama.cpp `llama-quantize` from the F16 merge.

	## Provenance & licensing

	Fine-tuned from HuggingFaceTB/SmolLM3-3B (Apache-2.0). Training data:
	[Glint-Research/Fable-5-traces](https://huggingface.co/datasets/Glint-Research/Fable-5-traces)
	(AGPL-3.0) and
	[Roman1111111/gpt5.5-terminal](https://huggingface.co/datasets/Roman1111111/gpt5.5-terminal)
	(MIT). Because those traces originate from third-party assistants, the
	providers' terms may apply to downstream training and distillation. If you
	plan to build on this model commercially, confirm your use aligns with those
	terms.

	## Citation

	```bibtex
	@misc{aglawe2026parable,
	author = {Aglawe, Ankit},
	title = {Agent-Trace Fine-Tuning of Small Language Models under Constrained Compute},
	year = {2026},
	doi = {10.5281/zenodo.21676407},
	url = {https://doi.org/10.5281/zenodo.21676407}
	}
	```

	## Acknowledgements

	The SmolLM3 team at Hugging Face for the base model; Glint-Research and
	Roman1111111 for the trace datasets; empero-ai for the recipe this series
	iterates on.