Llama-3.2-3B-Instruct-awq-g128-int4-asym-fp16-onnx-hybrid

Model details from ModelScope.ai for AMD/Llama-3.2-3B-Instruct-awq-g128-int4-asym-fp16-onnx-hybrid.

Not provided

Model metadata is served from the local cache (updated 2026-11-13).

Model size3.98 GiB

Storage3.98 GiB

Downloads254

Likes0

Basic information

Model repository: AMD/Llama-3.2-3B-Instruct-awq-g128-int4-asym-fp16-onnx-hybrid
Organization: AMD
Tasks: Not provided

Model type: Not provided
Architecture: Not provided
Libraries: onnx, pytorch
Base models: meta-llama/Llama-3.2-3B-Instruct
Current revision: master

License: llama3.2
Created: 2025-12-30
Last updated: 2026-11-11

ryzenai-hybrid

Not filled in locally.

Not filled in locally.

Not filled in locally.