Instructions to use Icodetools/Vulcan-1-coding-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 Icodetools/Vulcan-1-coding-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 Icodetools/Vulcan-1-coding-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Icodetools/Vulcan-1-coding-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 Icodetools/Vulcan-1-coding-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Icodetools/Vulcan-1-coding-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf Icodetools/Vulcan-1-coding-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf Icodetools/Vulcan-1-coding-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Icodetools/Vulcan-1-coding-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use Icodetools/Vulcan-1-coding-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Icodetools/Vulcan-1-coding-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": "Icodetools/Vulcan-1-coding-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Icodetools/Vulcan-1-coding-GGUF:Q4_K_M

Ollama
How to use Icodetools/Vulcan-1-coding-GGUF with Ollama:
```
ollama run hf.co/Icodetools/Vulcan-1-coding-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Icodetools/Vulcan-1-coding-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Icodetools/Vulcan-1-coding-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": "Icodetools/Vulcan-1-coding-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Icodetools/Vulcan-1-coding-GGUF with Docker Model Runner:
```
docker model run hf.co/Icodetools/Vulcan-1-coding-GGUF:Q4_K_M
```

Lemonade

How to use Icodetools/Vulcan-1-coding-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Icodetools/Vulcan-1-coding-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Vulcan-1-coding-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Icodetools/Vulcan-1-coding-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 Icodetools/Vulcan-1-coding-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 Icodetools/Vulcan-1-coding-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Icodetools/Vulcan-1-coding-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Icodetools/Vulcan-1-coding-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 "Icodetools/Vulcan-1-coding-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"

Vulcan-1-Coder (GGUF)

Results used no tools and a benchmarking harness. Also quantised to q8.

A 2.5B coding and reasoning model built by using Integer Space Artificial Selection on CherryPit 1.2, an already excellent model made by the team at DRUPEs. This model was generated and tested as a .gguf. Details of the method will be published later and released for all. I'm working hard to put everything together.

Made in an afternoon. Vulcan was produced in a single afternoon along with about 30 other models (12 in its class), all generated and tested in integer space, on a laptop with a 6 GB VRAM GPU, using only my own tools. No training runs, no cluster.

Every run, lasting just a few hours, resulted in success. The techique can work for all types of models. It's a data-led technique where the training is squeezed out rather than training it on more data. If the information exists in the model, we select for it.

Named after Vulcan, the Roman god of fire and the forge, the smith who crafts tools for the gods.

Safetensors version: coming soon.

Files

file	quant	size	notes
`Vulcan-1-Coder-Q4_K_M-league.gguf`	Q4_K_M	1.56 GB	the exact weights that won the selection league

Results

Notes: This model has not been fully tested or trained further after selection. It may have flaws or issues, for example one time it sent a bunch of symbols. But generally it scores high. All benchmarks are with no tools AND quantised.

AIME 2025

Run 1: 21 / 30 = 70.0% with thinking on, up to 24K tokens, temperature 1.0, 1 sample, Q8_0. Benchmarking harness. No tools. Per-problem results: Will add soon to a site I'm building.

AIME 2026

Notes: Although at this level, it could be noise, I wonder if selecting for the model at Q4_K_M found a model that's best at Q4_K_M. I'll get access to a better GPU soon and test.

Run 1: 23 / 30 = 76.7% with thinking on, up to 24K tokens, temperature 1.0, 1 sample, Q4_K_M. Benchmarking harness. No tools. Per-problem results: Will add soon to a site I'm building.

Run 2: 21 / 30 = 70.0% with thinking on, up to 24K tokens, temperature 1.0, 1 sample, Q8_0. Benchmarking harness. No tools. Per-problem results: Will add soon to a site I'm building.

Selection league

Scored on hard coding questions, plus some maths, agentic and reasoning tasks. No repeat questions and a large pool to avoid over-selecting for benchmarks. NO BENCHMARK QUESTIONS, all generated by Claude including some questions that are extremely hard. The league questions varied between models and the questions were not enough to find true representative results.

(0 / 0.5 / 1 per answer, Q4_K_M, temperature 1.0). Vulcan finished first. Plain CherryPit 1.2 is shown as the baseline. Note: While this is at the baseline, there are many generated models that were below it. CherryPit was chosen for a reason, it's well above its class.

model	score per question
Vulcan-1-Coder	0.763
CherryPit 1.2 (base)	0.611

Note: the league questions varied between models, so these scores are not fully representative of a head-to-head comparison. A like-for-like benchmark is coming.

Usage

Recommended sampling: temperature 1.0, top-p 0.95, thinking on. Give it room to think (16K+ tokens for hard problems): short limits cut off its answers.

Works in llama.cpp, LM Studio, Ollama and anything else that runs GGUF. Same architecture and size as CherryPit 1.2.

llama-server -m Vulcan-1-Coder-Q4_K_M-league.gguf -ngl 99 -c 32768 --jinja

For questions, contact ryan@filioai.com

Thanks

The team at DRUPEs for CherryPit 1.2, the base of Vulcan.
NANI-Nithin for the OpenCodeReasoning-2 LoRA adapter.
NVIDIA for the OpenCodeReasoning-2 dataset that adapter was trained on (CC-BY-4.0).

Things to come - progress

Paper and files released - 50%

Hand writing the paper and hand-making the diagrams without AI so I'll release it as soon as I can as a pre-print. I will remove secrets from the folder and clean it up. Folder currently has thousands of files and I'd say about 25% are relevant.

More benchmarks - ?

Whenever I feel up to it, adding some now.

Edit: Results from AIME 2026: Vulcan-1-Coder (Q4_K_M) benchmark harness no tools.

Settings: thinking on, max 24,000 tokens, temperature 1.0, top-p 0.95, 1 sample per problem, llama.cpp (CUDA).

problem	Vulcan's answer	correct answer	result	tokens used
A01	277	277	✓	2,020
A02	62	62	✓	4,937
A03	79	79	✓	3,468
A04	68	70	✗	3,198
A05	65	65	✓	2,848
A06	441	441	✓	2,155
A07	396	396	✓	4,241
A08	244	244	✓	3,317
A09	29	29	✓	17,086
A10	156	156	✓	9,186
A11	896	896	✓	11,527
A12	161	161	✓	18,540
A13	39	39	✓	23,518
A14	681	681	✓	7,540
A15	2	83	✗	7,237
A16	178	178	✓	1,914
A17	-	243	✗ (hit token limit)	24,000
A18	505	503	✗	8,668
A19	279	279	✓	5,581
A20	190	190	✓	7,950
A21	50	50	✓	4,905
A22	754	754	✓	5,987
A23	245	245	✓	10,713
A24	669	669	✓	5,061
A25	850	850	✓	6,960
A26	132	132	✓	8,593
A27	223	223	✓	10,525
A28	12	107	✗	17,496
A29	3	157	✗	18,535
A30	243	393	✗	15,340

Score: 23/30 = 76.7%

Quant perplexity-solver

Find the quants with the best perplexity

This unfortunately requires a runtime to go with it.

Further processing - 30%

I've discovered another technique that works to post-train one of these models. I'm still perfecting it but I'm already getting good results. I think the models can be optimised further.

Qwen 27b - 20%

Started the analysis process.

STEM - 50%

Static Embedding. Experimental native runtime for the .stem model format and embedding engine. The current runtime remains intentionally narrow: static embedding tables, token IDs, FP32 or INT8, mean pooling and optional L2. It is not yet a general-purpose encoder/ONNX/GGUF runner. It creates a .STEM format that is faster, smaller, and more accurate.

Licence

Released under the Apache License 2.0. Vulcan-1-Coder is a modified work that includes weights from:

DRUPEs/CherryPit-1.2-2B: Apache-2.0
openbmb/MiniCPM5-2B: Apache-2.0
NANI-Nithin/MiniCPM5-2B-OpenCodeReasoning2-LoRA: Apache-2.0 (trained on NVIDIA OpenCodeReasoning-2, CC-BY-4.0)
zzzluvst/MiniCPM5-2B-SWE-smith-GRPO: Apache-2.0
Caldalis/MiniCPM5-2B-Math: Apache-2.0

Downloads last month: 238

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

4-bit

Model tree for Icodetools/Vulcan-1-coding-GGUF

DRUPEs/CherryPit-1.2-2B

Merge model

this model