Instructions to use aparusel/ds4-kolibri-1-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 aparusel/ds4-kolibri-1-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 aparusel/ds4-kolibri-1-gguf
# Run inference directly in the terminal:
llama cli -hf aparusel/ds4-kolibri-1-gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf aparusel/ds4-kolibri-1-gguf
# Run inference directly in the terminal:
llama cli -hf aparusel/ds4-kolibri-1-gguf

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 aparusel/ds4-kolibri-1-gguf
# Run inference directly in the terminal:
./build/bin/llama cli -hf aparusel/ds4-kolibri-1-gguf

Use Docker

docker model run hf.co/aparusel/ds4-kolibri-1-gguf

Llama new
LM Studio
Jan

vLLM

How to use aparusel/ds4-kolibri-1-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aparusel/ds4-kolibri-1-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": "aparusel/ds4-kolibri-1-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aparusel/ds4-kolibri-1-gguf

Ollama
How to use aparusel/ds4-kolibri-1-gguf with Ollama:
```
ollama run hf.co/aparusel/ds4-kolibri-1-gguf
```
Unsloth Desktop

How to use aparusel/ds4-kolibri-1-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aparusel/ds4-kolibri-1-gguf

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": "aparusel/ds4-kolibri-1-gguf"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use aparusel/ds4-kolibri-1-gguf with Docker Model Runner:
```
docker model run hf.co/aparusel/ds4-kolibri-1-gguf
```

Lemonade

How to use aparusel/ds4-kolibri-1-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull aparusel/ds4-kolibri-1-gguf

Run and chat with the model

lemonade run user.ds4-kolibri-1-gguf-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use aparusel/ds4-kolibri-1-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 aparusel/ds4-kolibri-1-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 aparusel/ds4-kolibri-1-gguf

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use aparusel/ds4-kolibri-1-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aparusel/ds4-kolibri-1-gguf

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 "aparusel/ds4-kolibri-1-gguf" \
  --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"

Kolibri-1 GGUF (Q8 / Q4 / Q2) — DwarfStar format

Quantized GGUF builds of Aleph-Alpha/Kolibri-1 — Aleph Alpha's 78.10B-parameter (3.46B active) German/English MoE reasoning model — converted from the FP8 release at revision e52eb4627d11516b0c01de49210ab5a4e4061444 with DwarfStar's kolibri1_quantize.py. The weights are modified (quantized) relative to the original release.

These are DwarfStar (ds4) format GGUFs. They load with the ds4 inference engine (Metal or CPU reference) and are not generic llama.cpp-compatible GGUF files.

File	Routed experts	Attention / shared / output	Size	SHA-256
`Kolibri-1-Q8.gguf`	Q8_0	Q8_0, F32 norms/router	77.42 GiB (83,135,396,224 B)	`e33fb57c3ea7dfba7692e9a7055632cebf96625e1753d1b900e73db0ee6a03d8`
`Kolibri-1-Q4.gguf`	Q4_K	Q8_0, F16 embedding, F32 norms/router	42.56 GiB (45,693,860,224 B)	`0b3d5bf9ae13b467be4fa4c8f63208a2fd837577d6ec2e1c636cbf185aa26930`
`Kolibri-1-Q2.gguf`	IQ2_XXS gate/up, Q2_K down	Q8_0, F16 embedding, F32 norms/router	22.78 GiB (24,460,196,256 B)	`5aa002fc9c852a91fc47b3aaa04717dfb6d30001fcc1b85a33bbfe9cfa19cdb5`

Suggested order of preference: Q8 (closest to the release, ~78 GB of weights), Q4 (good quality/size trade-off), Q2 (smallest; quantized with the weight-energy bootstrap since no imatrix was used).

Running

Kolibri-1 support is not merged upstream yet; it lives in the main branch of aparusel/ds4-kolibri-1 for now. Build that fork and point it at a file:

git clone https://github.com/aparusel/ds4-kolibri-1 ds4
cd ds4 && make

./ds4 -m /path/to/Kolibri-1-Q4.gguf
./ds4-server -m /path/to/Kolibri-1-Q4.gguf --ctx 32768

Kolibri-1 runs on Metal and the CPU reference backend (ds4 --cpu -m ...). CUDA, ROCm, tensor/pipeline parallelism, SSD streaming, speculation and vision are not supported for this model. Thinking is on by default; --think-level N maps to the released low/medium/high effort wording, and the model defaults to temperature 1, top-p 0.97, top-k 128. See docs/MODELS.md for details.

How these were produced

make -C gguf-tools libds4quants.dylib
python3 gguf-tools/kolibri1_quantize.py \
  --hf models/Kolibri-1 \
  --source-revision e52eb4627d11516b0c01de49210ab5a4e4061444 \
  --out gguf/Kolibri-1-Q4.gguf --quant q4

Every released tensor must be claimed exactly once, and only the exact source snapshot matching the plan is accepted, which is why the source revision is pinned above. Each artifact can be audited with gguf-tools/kolibri1_validate_gguf.py --payload.

License and attribution

The model weights are published by Aleph Alpha GmbH under the Apache 2.0 license; the license text is included in LICENSE. This repository redistributes modified copies (quantized conversions) under the same license, with attribution, and states the changes as required by section 4(b) of the license. It is an unofficial community conversion and is not affiliated with or endorsed by Aleph Alpha.

The original model card contains the Responsible Use section, intended use, risks and limitations; please read it before deployment. The Apache 2.0 grant applies only to the weights and configuration files published by Aleph Alpha — it does not extend to their underlying code, model architecture, parameter settings or training methods.

Downloads last month: 499

GGUF

Model size

78B params

Architecture

kolibri1

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for aparusel/ds4-kolibri-1-gguf

Base model

Aleph-Alpha/Kolibri-1-BF16

Quantized

Aleph-Alpha/Kolibri-1

Quantized

(28)

this model