Hugging Face's logo

twistlabs
/
fotometis-qwen-3.5-0.8b-mlx

MLX
Safetensors
qwen3_5
fotometis
tool-use
8-bit precision
Model card Files
xet
 Community
How to use from the
Use from the
MLX library
# Download the model from the Hub
pip install huggingface_hub[hf_xet]

huggingface-cli download --local-dir fotometis-qwen-3.5-0.8b-mlx twistlabs/fotometis-qwen-3.5-0.8b-mlx

twistlabs/fotometis-qwen-3.5-0.8b-mlx

The develop assistant in Fotometis, a raw photo editor.

version v1
quantization 8-bit, group 64
on disk 1.0 GB
vocabulary depth known
thinking trained both ways — either toggle
rendering rules R12
Downloads last month
20
Safetensors
Model size
0.9B params
Tensor type
U32
·
BF16
·
MLX
Hardware compatibility
Log In to add your hardware

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for twistlabs/fotometis-qwen-3.5-0.8b-mlx

Base model

Qwen/Qwen3.5-0.8B-Base
Finetuned
Qwen/Qwen3.5-0.8B
Quantized
(235)
this model