Modelpublic

LibraxisAI/svetliq-11b-v3-evolutionary-preview-mlx-q8

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face

0likes9downloads

Model Card

svetliq-11b-v3-evolutionary-preview-mlx-q8

svetliq-11b-v3-evolutionary-preview-mlx-q8 is a Polish veterinary clinical checkpoint in MLX format, derived from speakleash/Bielik-11B-v2.6-Instruct and packaged for local Apple Silicon inference.

Intended use

—Polish veterinary clinical drafting and case reasoning for practitioner review
—Differential diagnosis, triage notes, drug-reference style explanations, and care-plan drafts
—Local Apple Silicon inference where data locality and operator control matter

Out of scope

—Direct-to-owner veterinary diagnosis or treatment decisions
—Languages other than Polish unless independently evaluated
—Safety-critical decisions without domain expert review
—Claims of benchmark superiority not backed by published evaluation data
—Non-MLX runtime guarantees; this card documents the shipped HF checkpoint, not every possible serving stack

Training and conversion metadata

Parameter	Value
Repository	`LibraxisAI/svetliq-11b-v3-evolutionary-preview-mlx-q8`
Base model	`speakleash/Bielik-11B-v2.6-Instruct`
Task	`text-generation`
Library	`mlx`
Format	MLX / Apple Silicon checkpoint
Quantization	Q8
Architecture	LlamaForCausalLM
Model files	3
Config model_type	`llama`

This card only reports metadata present in the Hugging Face repository, existing card frontmatter, or public config files. Missing benchmark, dataset, or training-run details are left explicit rather than reconstructed.

Usage

CLI

bash

pip install mlx-lm

mlx_lm.generate \
  --model LibraxisAI/svetliq-11b-v3-evolutionary-preview-mlx-q8 \
  --prompt "Opisz krótko objawy odwodnienia u psa i kiedy pilnie skontaktować się z lekarzem weterynarii." \
  --max-tokens 400

Python

python

from mlx_lm import load, generate

model, tokenizer = load("LibraxisAI/svetliq-11b-v3-evolutionary-preview-mlx-q8")

prompt = "Opisz krótko objawy odwodnienia u psa i kiedy pilnie skontaktować się z lekarzem weterynarii."
response = generate(model, tokenizer, prompt=prompt, max_tokens=400)
print(response)

Multi-turn with the chat template

This checkpoint follows the tokenizer/chat-template contract inherited from speakleash/Bielik-11B-v2.6-Instruct when the template is present in the repository:

python

from mlx_lm import load, generate

model, tokenizer = load("LibraxisAI/svetliq-11b-v3-evolutionary-preview-mlx-q8")

messages = [
    {"role": "user", "content": "Opisz krótko objawy odwodnienia u psa i kiedy pilnie skontaktować się z lekarzem weterynarii."},
]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
response = generate(model, tokenizer, prompt=prompt, max_tokens=400)
print(response)

Example output

No public sample output is currently declared for this checkpoint. Run the usage example above against your own prompt or audio/image input to inspect behavior.

Comparison with the base model

Aspect	Base	This checkpoint
Lineage	`speakleash/Bielik-11B-v2.6-Instruct`	Polish veterinary-domain checkpoint in MLX format
Domain emphasis	General instruction behavior from the base family	Veterinary clinical drafting, Polish case reasoning, and practitioner-facing assistance
Published benchmark delta	Not declared in public metadata	Not declared in public metadata

Limitations

—No public benchmarks for this checkpoint are declared in the model metadata.
—No public benchmark claims are made by this card unless listed in the frontmatter.
—Validate outputs on your own domain data before relying on this checkpoint.
—Memory use and speed depend heavily on the exact Apple Silicon generation, unified-memory size, and prompt length.
—Veterinary outputs require review by a licensed veterinarian.

License

apache-2.0. Check the upstream/base model license as well when a base model is declared.

Citation

bibtex

@misc{libraxisai-svetliq-11b-v3-evolutionary-preview-mlx-q8,
  title = {svetliq-11b-v3-evolutionary-preview-mlx-q8},
  author = {LibraxisAI},
  year = {2026},
  howpublished = {\url{https://huggingface.co/LibraxisAI/svetliq-11b-v3-evolutionary-preview-mlx-q8}},
  note = {MLX checkpoint published by LibraxisAI}
}

Inference tested on

`LibraxisAI/mlx-batch-server`

—Base model: `speakleash/Bielik-11B-v2.6-Instruct`