inference-optimization
/

Llama-3.2-3B-Instruct-6-bits-mode-hybrid-per-tensor

compressed-tensors

Model card Files Files and versions

Llama-3.2-3B-Instruct-6-bits-mode-hybrid-per-tensor / tokenizer.json

Commit History

Upload HIGGS per-tensor quantized model

0b815f8
verified

krishnateja95 commited on Apr 22