matmelis
/

Llama_3.2_3B_w_int3_qronos

8-bit precision

Model card Files Files and versions

[INFO] Perplexity: 9.14197826385498

Downloads last month: 16

Safetensors

Model size

1.48B 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_3B_w_int3_qronos

Base model

meta-llama/Llama-3.2-3B

Quantized

(101)

this model

Collection including matmelis/Llama_3.2_3B_w_int3_qronos

Llama-3.2 Qronos

9 items • Updated 15 days ago