matmelis
/

Llama_3.2_1B_w_int3_gptq

8-bit precision

Model card Files Files and versions

[INFO] Perplexity: 13.088748931884766

Downloads last month: 12

Safetensors

Model size

638M params

Tensor type

F32

·

BF16

·

U8

·

Inference Providers NEW

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

Model tree for matmelis/Llama_3.2_1B_w_int3_gptq

Base model

meta-llama/Llama-3.2-1B

Quantized

(207)

this model

Collection including matmelis/Llama_3.2_1B_w_int3_gptq

Llama-3.2 GPTQ

9 items • Updated 25 days ago