EXL3 quantization of reka-flash-3, 3 bits per weight.

Model	Q4	Q8	FP16
reka-flash-3-exl3-3bpw	87.8	90.2	90.9
reka-flash-3-exl3-4bpw	89.0	88.4	87.2

Safetensors

Model size

4.55B params

Tensor type

F16

I16

Inference Providers NEW

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

Model tree for isogen/reka-flash-3-exl3-3bpw

Base model

Quantized

(29)

this model