Downloads · 30 days
28
12% of all-time downloads
borealis-4b-instruct-preview-mlx-8bit
NbAiLab/borealis-4b-instruct-preview-mlx-8bit
borealis-4b-instruct-preview-mlx-8bit is a text generation model from NbAiLab. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as gemma.
All-time downloads
233
Public
Parameters
3.9B
4.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.4 GB · 99%
Parameter types
How the weights are stored.
U323.9B · 100%
Base models
Datasets
Model card
From the Hugging Face model README
Borealis 4B Instruct MLX (Preview)
Release: Dec 22nd, 2025.
Model summary
NbAiLab/borealis-4b-instruct-preview-mlx is a MLX 8bit quantized version of a 4B-parameter instruction-tuned preview model intended for early testing and feedback. It is an experiment and should be treated as pre-release quality.
The original model is NbAiLab/borealis-4b-instruct-preview.
| Model | Bits | Format |
|---|---|---|
| NbAiLab/borealis-4b-instruct-preview | BF16 | Transformers (safetensors) |
| NbAiLab/borealis-4b-instruct-preview-gguf | 8 | GGUF (q8_0) |
| NbAiLab/borealis-4b-instruct-preview-gguf | 16 | GGUF (f16) |
| NbAiLab/borealis-4b-instruct-preview-gguf | BF16 | GGUF (bf16) |
| NbAiLab/borealis-4b-instruct-preview-mlx | 32 | MLX |
| NbAiLab/borealis-4b-instruct-preview-mlx-8bits | 8 | MLX (quantized) |
This model NbAiLab/borealis-4b-instruct-preview-mlx-8bits was converted to MLX format from NbAiLab/borealis-4b-instruct-preview using mlx-lm version 0.29.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("NbAiLab/borealis-4b-instruct-preview-mlx-8bits")
prompt = "hei :)"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
- Task
- Text Generation
- Library
- mlx
- Type
- gemma3
- License
- gemma
- Languages
- no, nb, nn
- Created
- Dec 22, 2025
- Updated
- Dec 23, 2025