Meta Llama3.2 3B Instruct ONNX INT4 RTX TensorRT Model Optimizer

Meta

Meta Llama 3.2 3B Instruct INT4 ONNX model is the quantized version of the Meta Llama-3.2-3B-Instruct model, which is an auto-regressive language model that uses an optimized transformer architecture.

Runs on RTX

Name	Size	Updated	Actions
3rd_party_licenses.txt	2.34 KB	February 28, 2025 UTC	curl wget Download
Acceptable_use_policy.txt	41 B	February 28, 2025 UTC	curl wget Download
genai_config.json	1.7 KB	February 28, 2025 UTC	curl wget Download
License.txt	366 B	February 28, 2025 UTC	curl wget Download
model.onnx	308.75 KB	February 28, 2025 UTC	curl wget Download
model.onnx_data	2.85 GB	February 28, 2025 UTC	curl wget Download
notice.txt	121 B	February 28, 2025 UTC	curl wget Download
Readme.txt	536 B	February 28, 2025 UTC	curl wget Download
special_tokens_map.json	312 B	February 28, 2025 UTC	curl wget Download
tokenizer_config.json	55.26 KB	February 28, 2025 UTC	curl wget Download
tokenizer.json	9.06 MB	February 28, 2025 UTC	curl wget Download