mlx-gen
Collection
Models prepared and quantized for Apple MLX by mlx-gen based on mflux. https://github.com/lpalbou/mlx-gen • 30 items • Updated
# Download the model from the Hub
pip install huggingface_hub[hf_xet]
huggingface-cli download --local-dir fibo-4bit AbstractFramework/fibo-4bitFIBO 4-bit for MLX-Gen
This repository contains MLX-Gen saved weights for briaai/FIBO.
It is designed for local Apple Silicon inference with mlx-gen.
This is an MLX-Gen/mflux saved-weight folder, not a Diffusers or Transformers
from_pretrained() checkpoint.
License and access
This checkpoint is a quantized derivative of the gated briaai/FIBO source model and follows the
source model's bria-fibo non-commercial license terms. Access to this derivative should require
users to accept the upstream FIBO terms before downloading the files.
Capability
This package is for base FIBO text-to-image generation only.
FIBO Edit is a separate upstream model family and is not included in this package. Current MLX-Gen
public capability discovery intentionally does not expose FIBO Edit through unified mlxgen generate
until source-model and prepared-package edit validation pass.
Quantization
This is a mixed q4/BF16 FIBO package:
- q4 for quantizable FIBO transformer and text-encoder linears.
- BF16 for the VAE.
- BF16 for FIBO conditioning, timestep, caption-projection, normalization, and output-projection paths that are precision-sensitive in MLX-Gen.
Validation
Measured on an Apple M5 Max with 128 GB unified memory using mlx-gen 0.18.11.
Prompt file: validation/fibo_seed103_prompt.json
Settings: width=512, height=512, steps=8, guidance=5, seed=103.
| Package | Disk | Time | Max RSS | MAE vs source |
|---|---|---|---|---|
Source briaai/FIBO |
23.8 GiB cache | 15.13 s | 24.13 GB | baseline |
| q8/BF16 package | 14.5 GiB | 16.45 s | 15.89 GB | 8.81 |
| This q4/BF16 package | 10.2 GiB | 15.24 s | 11.39 GB | 17.56 |
Detailed validation notes: validation/fibo_base_q8_q4_seed103_metrics.md
Usage
python -m pip install -U mlx-gen
mlxgen download --model AbstractFramework/fibo-4bit
mlxgen generate \
--model AbstractFramework/fibo-4bit \
--prompt-file validation/fibo_seed103_prompt.json \
--width 512 \
--height 512 \
--steps 8 \
--guidance 5 \
--seed 103 \
--output fibo-q4.png
Attribution
FIBO is published by Bria.ai. MLX-Gen is based on mflux by Filip Strand and the original mflux contributors.
Quantized and contributed by @lpalbou.
Hardware compatibility
Log In to add your hardware
4-bit
Model tree for AbstractFramework/fibo-4bit
Unable to build the model tree, the base model loops to the model itself. Learn more.
# Gated model: Login with a HF token with gated access permission hf auth login