twistlabs/fotometis-qwen-3.5-9b-mlx

The develop assistant in Fotometis, a raw photo editor.


version	`v1`
quantization	4-bit, group 64
on disk	6.0 GB
vocabulary depth	`known`
thinking	trained both ways — either toggle
rendering rules	R9

Safetensors

Model size

9B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for twistlabs/fotometis-qwen-3.5-9b-mlx

Base model

Finetuned

Quantized

(490)

this model