Official AQLM quantization of meta-llama/Llama-3.2-3B finetuned with PV-Tuning.

For this quantization, we used 2 codebooks of 8 bits and groupsize of 8.

Results:

Model	Quantization	MMLU (5-shot)	ArcC	ArcE	Hellaswag	PiQA	Winogrande	Model size, Gb
meta-llama/Llama-3.2-3B-Instruct	fp16	0.5984	0.4369	0.7428	0.5224	0.7579	0.6732	6.4
	2x8g8	0.4842	0.3686	0.7066	0.4833	0.7274	0.6346	1.5

Safetensors

Model size

1.1B params

Tensor type

FP16

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

Model tree for ISTA-DASLab/Llama-3.2-3B-Instruct-AQLM-PV-2Bit-2x8

Base model

Quantized

(268)

this model

Collection including ISTA-DASLab/Llama-3.2-3B-Instruct-AQLM-PV-2Bit-2x8