Llama 3.2 1B Instruct Genie W4A16 for Snapdragon 8 Elite Gen 5

What is included

• Quantized Genie binary shards (*.bin)
• genie_config.json
• htp_backend_ext_config.json
• config.json
• tokenizer.json
• tokenizer_config.json
• metadata.yaml
• sample_prompt.txt

Runtime and packaging

• Runtime: Qualcomm Genie
• Backend: QNN HTP (QnnHtp)
• Target device family: Qualcomm Snapdragon 8 Elite Gen 5
• Target code: qualcomm_snapdragon_8_elite_gen5
• Context length: 4096
• Vocabulary size: 128256
• Packaging: W4A16 Genie bundle
• QAIRT version: 2.42.0.251225135753_193295

Base model

• Base model: meta-llama/Llama-3.2-1B-Instruct
• Architecture: LlamaForCausalLM
• Hidden size: 2048
• Number of layers: 16
• Attention heads: 32
• KV heads: 8
• Torch dtype in config: bfloat16

Usage notes

Example prompt

Provenance and licensing

• Imported from Qualcomm AI Hub artifacts
• Derived from meta-llama/Llama-3.2-1B-Instruct
• Review the upstream Meta Llama license terms and any Qualcomm AI Hub redistribution requirements before production use