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

Safetensors

Model size

0.3B params

Tensor type

BF16

U32

MLX

Hardware compatibility

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

Finetuned

Quantized

(235)

this model