DevQuasar
/

meta-llama.Llama-3.1-8B-Instruct-NVFP4A16

Text Generation

8-bit precision

compressed-tensors

Model card Files Files and versions

'Make knowledge free for everyone'

Made with llmcompressor

Quantized version of: meta-llama/Llama-3.1-8B-Instruct

Downloads last month: 215

Safetensors

Model size

4.98B params

Tensor type

BF16

·

F32

·

F8_E4M3

·

U8

·

Model tree for DevQuasar/meta-llama.Llama-3.1-8B-Instruct-NVFP4A16

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Quantized

(496)

this model