ekryski
/

diar_streaming_sortformer_4spk-v2.1-4bit

4-bit precision

Model card Files Files and versions

diar_streaming_sortformer_4spk-v2.1-4bit

4-bit affine quantization of mlx-community/diar_streaming_sortformer_4spk-v2.1-fp16, produced with FFAI 0.1.0's ffai convert (mlx-affine format, group_size=64).

Conversion

ffai convert mlx-community/diar_streaming_sortformer_4spk-v2.1-fp16 --bits 4 \
    --upload-repo ekryski/diar_streaming_sortformer_4spk-v2.1-4bit

See also

FFAI — fast Apple Silicon LLM inference. Model.load("ekryski/diar_streaming_sortformer_4spk-v2.1-4bit") runs this checkpoint end-to-end.
FFAI quickstart
FFAI quantization docs

Downloads last month: 11

Safetensors

Model size

30.2M params

Tensor type

F16

·

U32

·

MLX

Hardware compatibility

Log In to add your hardware

4-bit

Inference Providers NEW

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

Model tree for ekryski/diar_streaming_sortformer_4spk-v2.1-4bit

Base model

nvidia/diar_streaming_sortformer_4spk-v2.1

Finetuned

mlx-community/diar_streaming_sortformer_4spk-v2.1-fp16

Quantized

(1)

this model