Instructions to use Norika1207/Bragi-LLM-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Norika1207/Bragi-LLM-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Norika1207/Bragi-LLM-GGUF",
	filename="c15v-q3km-imat.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 Norika1207/Bragi-LLM-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Norika1207/Bragi-LLM-GGUF
# Run inference directly in the terminal:
llama-cli -hf Norika1207/Bragi-LLM-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Norika1207/Bragi-LLM-GGUF
# Run inference directly in the terminal:
llama-cli -hf Norika1207/Bragi-LLM-GGUF

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 Norika1207/Bragi-LLM-GGUF
# Run inference directly in the terminal:
./llama-cli -hf Norika1207/Bragi-LLM-GGUF

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 Norika1207/Bragi-LLM-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Norika1207/Bragi-LLM-GGUF

Use Docker

docker model run hf.co/Norika1207/Bragi-LLM-GGUF

LM Studio
Jan

vLLM

How to use Norika1207/Bragi-LLM-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Norika1207/Bragi-LLM-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": "Norika1207/Bragi-LLM-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Norika1207/Bragi-LLM-GGUF

Ollama
How to use Norika1207/Bragi-LLM-GGUF with Ollama:
```
ollama run hf.co/Norika1207/Bragi-LLM-GGUF
```

Unsloth Studio

How to use Norika1207/Bragi-LLM-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 Norika1207/Bragi-LLM-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 Norika1207/Bragi-LLM-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Norika1207/Bragi-LLM-GGUF to start chatting

How to use Norika1207/Bragi-LLM-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Norika1207/Bragi-LLM-GGUF

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": "Norika1207/Bragi-LLM-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Norika1207/Bragi-LLM-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Norika1207/Bragi-LLM-GGUF

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 Norika1207/Bragi-LLM-GGUF

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Norika1207/Bragi-LLM-GGUF with Docker Model Runner:
```
docker model run hf.co/Norika1207/Bragi-LLM-GGUF
```

Lemonade

How to use Norika1207/Bragi-LLM-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Norika1207/Bragi-LLM-GGUF

Run and chat with the model

lemonade run user.Bragi-LLM-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Bragi-LLM-GGUF

An 805 MB local Python coding assistant. 92% MBPP single-shot, 2 points behind Qwen2.5-Coder-7B (14 GB, 17x larger). Zero API cost.

What is this

c15v-q3km-imat.gguf is the backbone GGUF for the Bragi-LLM system, a 786 MB Q3_K_M quantised Qwen2.5-Coder-1.5B-Instruct with imatrix calibration on MBPP-train Python code. It is the small LLM half of a hybrid design: combined with a 15 KB hand-engineered symbolic engine library and a 6 KB keyword intercept router, the full system reaches 92% pass@1 on the MBPP test split, single-shot greedy decoding, no retry. See the paper for the failure-mode analysis and ablations: doi:10.5281/zenodo.20557449.

The triptych

Role	Repo	What it is
Brain (this file)	Bragi-LLM	The 805 MB local Python coder.
Eyes	Code Tree	The visual IDE.
Hands	Demeter-CodeBuilder	OpenAI-compatible proxy wiring Bragi as Code Tree's default local backend.

Together: about 1 GB on disk. Fully offline. Zero recurring fees. MIT.

Results

System	Footprint	MBPP test 0-99 single-shot
Vanilla 1.5B Q3_K_M (this backbone alone)	786 MB	65%
With intercept router + engine_lib (full Bragi system)	805 MB	92%
Reference Qwen2.5-Coder-7B fp16	14 GB	94%

The GGUF alone (this file) is the 65% column. The 92% number requires the router and engine library which are open-sourced in the Bragi-LLM GitHub repo.

Quick start

Download

huggingface-cli download norika1207-lab/Bragi-LLM-GGUF c15v-q3km-imat.gguf --local-dir .

Run with llama.cpp

# build llama.cpp once
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp && cmake -B build && cmake --build build --config Release

# serve
./build/bin/llama-server -m c15v-q3km-imat.gguf -ngl 99 -c 16384 --parallel 4 --port 8080
# CPU only
./build/bin/llama-server -m c15v-q3km-imat.gguf -ngl 0  -c 16384 --parallel 4 --port 8080

Use full Bragi system (recommended, gets 92%)

Combine with router and engine library from the GitHub repo:

git clone https://github.com/norika1207-lab/Bragi-LLM
cd Bragi-LLM
python3 solve_intercept2.py 1 1 100 http://localhost:8080/v1/chat/completions

Or use the OpenAI-compatible proxy from Demeter-CodeBuilder, which wraps everything and exposes Bragi as a drop-in OpenAI endpoint.

How it works

The 1.5B Q3 backbone alone fails MBPP problems primarily by mis-recalling rare formulas: octagonal number written as 3n^2 - 2n instead of n(3n - 2), divisibility-by-11 implemented as digit-sum-mod-11 (correct rule is alternating digit sum). These formulas are 50-byte Python expressions; storing them in 3-bit quantised weights is wasteful and error-prone.

The full Bragi system externalises rare formulas into a 15 KB symbolic library (engine_lib.py) and routes matched problems entirely around the LLM via a regex keyword router. The backbone runs only when no route matches.

Quantisation details

Base model: Qwen/Qwen2.5-Coder-1.5B-Instruct
Quantisation: Q3_K_M with imatrix calibration
Imatrix corpus: MBPP-train Python code split (374 verified solutions, 67 KB; no test data)
Tool: llama.cpp llama-imatrix + llama-quantize build b4c0549
File size: 786 MB

Limitations

Hand-engineered engine_lib covers the MBPP test distribution but not arbitrary code tasks.
Regex router will not match prompts in other languages or with unusual phrasing.
Real-world coding (multi-file refactoring, integration with existing codebases) is not measured by MBPP and not the design target.

See paper section 5.3 for full limitations.

Citation

@misc{chen2026bragillm,
  author = {Chen, Ho Yiing},
  title  = {Bragi-LLM: An 805 MB Hybrid Code-Generation System Reaches 92\% MBPP via LLM-Symbolic Engine Routing},
  year   = {2026},
  doi    = {10.5281/zenodo.20557449},
  url    = {https://doi.org/10.5281/zenodo.20557449},
  note   = {Independent Researcher, Taiwan. ORCID 0009-0006-6816-9891.}
}

Author

Chen, Ho Yiing (norika), Independent Researcher, Taiwan. ORCID: 0009-0006-6816-9891

Correspondence: norika at charenix.com

License

MIT. See the Bragi-LLM repo for the full LICENSE file.

Acknowledgements

Developed using donated off-hours access to NVIDIA DGX Spark hardware. Implementation and draft writing assisted by Claude (Anthropic). The architectural direction (refuse to ship sub-target results, diagnose before optimising, externalise rather than memorise) is the author's.

Downloads last month: 302

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for Norika1207/Bragi-LLM-GGUF

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B-Instruct

Quantized

(103)

this model