LibraxisAI/Bielik-11B-v3.0-mlx-bf16

Bielik-11B-v3.0-Instruct MLX (bf16)

MLX conversion of speakleash/Bielik-11B-v3.0-Instruct for Apple Silicon.

Model Details

Property	Value
Original Model	speakleash/Bielik-11B-v3.0-Instruct
Format	MLX bfloat16
Size	~22 GB
Peak Memory	~22.4 GB
Generation Speed	~27 tok/s (M3 Ultra)

Other Quantizations

Variant	Size	Memory	Link
bf16 (this)	22 GB	22.4 GB	-
q8	11 GB	11.9 GB	LibraxisAI/Bielik-11B-v3.0-mlx-q8
q5	7.2 GB	7.8 GB	LibraxisAI/Bielik-11B-v3.0-mlx-q5
mxfp4	5.5 GB	6.0 GB	LibraxisAI/Bielik-11B-v3.0-mlx-mxfp4
q4	5.9 GB	6.4 GB	LibraxisAI/Bielik-11B-v3.0-mlx-q4

Usage

# Install mlx-lm
pip install mlx-lm

# Generate
mlx_lm.generate --model LibraxisAI/Bielik-11B-v3.0-mlx-bf16 --prompt "Cześć, jak się masz?"

# Chat
mlx_lm.chat --model LibraxisAI/Bielik-11B-v3.0-mlx-bf16

from mlx_lm import load, generate

model, tokenizer = load("LibraxisAI/Bielik-11B-v3.0-mlx-bf16")
response = generate(model, tokenizer, prompt="Wyjaśnij czym jest sztuczna inteligencja.", max_tokens=256)
print(response)

About Bielik

Bielik is a Polish language model developed by SpeakLeash. This conversion enables native execution on Apple Silicon Macs using the MLX framework.

License

Apache 2.0 - see original model for terms.

---

Converted by LibraxisAI using mlx-lm