Instructions to use rty813/Kolibri-1-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rty813/Kolibri-1-bf16 with Transformers:

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

pipe = pipeline("text-generation", model="rty813/Kolibri-1-bf16")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rty813/Kolibri-1-bf16")
model = AutoModelForCausalLM.from_pretrained("rty813/Kolibri-1-bf16", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rty813/Kolibri-1-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rty813/Kolibri-1-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rty813/Kolibri-1-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rty813/Kolibri-1-bf16

SGLang

How to use rty813/Kolibri-1-bf16 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 "rty813/Kolibri-1-bf16" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rty813/Kolibri-1-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "rty813/Kolibri-1-bf16" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rty813/Kolibri-1-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rty813/Kolibri-1-bf16 with Docker Model Runner:
```
docker model run hf.co/rty813/Kolibri-1-bf16
```

Kolibri-1-bf16 (bf16)

Full-precision (bf16) PyTorch port of Aleph-Alpha/Kolibri-1, for vLLM / TGI / Xinference / transformers users who don't want the GGUF quant.

Format: pytorch_model.bin (bf16). safetensors conversion in progress.
Architecture: identical to the original — drop-in for AutoModelForCausalLM.from_pretrained("rty813/Kolibri-1-bf16").
Also loads in vLLM (vllm serve rty813/Kolibri-1-bf16) and Xinference (search "Kolibri-1").

Original model card:

license: "apache-2.0" pipeline_tag: text-generation library_name: vllm base_model: Aleph-Alpha/Kolibri-1-BF16 tags: - reasoning - moe language: - de - en

Kolibri

Tech report | Tech blog

Kolibri is Aleph Alpha's mixture-of-experts (MoE) reasoning model, with a focus on German and English. The model supports an explicit reasoning mode and tool calling. It is optimized for long-context and inference efficiency.

Model overview

Model	Kolibri 1
Model Provider	Aleph Alpha GmbH
Model Developer	Aleph Alpha Research GmbH
Architecture	Mixture-of-Experts
Total parameters	78B (`78,103,074,560`)
Active parameters / token	3.46B (`3,457,573,120`)
Languages	German, English
Context length	`1,048,576 tokens`; we recommend ≤262,144 tokens for serving efficiency and complex tasks
Precision	`float8_e4m3fn` weights in 128×128 blocks with dynamically quantized activations, evaluated with an FP8 KV cache; embeddings, LM head, norms and MoE router in `bfloat16`
Reasoning mode	Yes
Tool calling	Yes
License	Apache 2.0
Knowledge cutoff	EN: June 18, 2026, DE: June 18, 2026 This only affects implicit knowledge, the model may use more recent information through tool use.
Hardware requirements	Model memory footprint: ~78 GB (FP8 weights). Minimum: 2

Downloads last month: 41

Model tree for rty813/Kolibri-1-bf16

Base model

Aleph-Alpha/Kolibri-1-BF16

Quantized

Aleph-Alpha/Kolibri-1

Quantized

(24)

this model