Qualcomm Snapdragon 8 Gen 3
Flagship Android SoC. Hexagon NPU at 45 TOPS INT8. First mainstream phone NPU to run 7B-class models on-device via Qualcomm AI Hub + ONNX Runtime Mobile.
Qualcomm Snapdragon 8 Gen 3
Affiliate disclosure: as an Amazon Associate and partner of other retailers, we earn from qualifying purchases. The verdict on this page is our editorial opinion; affiliate links never influence what we recommend.
Extrapolated from 76.8 GB/s bandwidth — 6.1 tok/s estimated. No measured benchmarks yet.
Plain-English: Doesn't fit modern chat models usefully.
Verdicts extrapolated from catalog VRAM + bandwidth + ecosystem flags. Hover any chip for the rationale. Want measured numbers? Submit your own run with runlocalai-bench --submit.
What it does well
The Qualcomm Snapdragon 8 Gen 3 is the 2024 flagship Android phone SoC, prior generation to Snapdragon 8 Elite. 1× Cortex-X4 + 5× Cortex-A720 + 2× Cortex-A520 CPU + Adreno 750 GPU + dedicated Hexagon NPU rated at 45 TOPS. Shipped in 2024 flagship Android phones — Samsung Galaxy S24 Ultra, OnePlus 12, Xiaomi 14 Pro, ASUS ROG Phone 8 at $899-$1,399 retail. The chip established the on-device AI feature template that 8 Elite refined: Google Gemini Nano integration, Samsung Galaxy AI, OEM-specific transformer-based features. Used phones with 8 Gen 3 in 2026 are excellent value at $400-$700 — the AI capability is essentially identical to 8 Elite for typical on-device features.
Where it breaks
- Architecture is one generation behind 8 Elite. Same NPU TOPS rating but lower CPU + GPU peak performance. For non-AI phone use, 8 Gen 3 vs 8 Elite is meaningful; for on-device AI features specifically, the gap is small.
- All the standard phone SoC limitations apply — phone form factor, sandboxed runtime, no proper development workflow.
- Memory ceiling at 12-16 GB.
- End-of-feature-support window approaching. Phone SoCs typically get 3-5 years of OEM software support; 8 Gen 3 is 2 years into that window in 2026.
Ideal model range
- Sweet spot: Sub-3B class on-device inference. Same as 8 Elite for typical features.
- Sweet spot: Used Android phones with 8 Gen 3 at $400-$700 in 2026 — value pick for AI-curious phone buyers.
- Bad fit: Same as all phone SoCs — phones aren't AI development hardware.
Verdict
Buy a phone with Snapdragon 8 Gen 3 for the value used phone use case in 2026 — the on-device AI features (Gemini Nano, Samsung Galaxy AI) work essentially identically to 8 Elite at meaningfully lower price.
Skip this if you want current-gen phone silicon (Snapdragon 8 Elite), or you're shopping for AI development hardware (wrong tier entirely).
How it compares
- vs Snapdragon 8 Elite → 8 Elite has higher CPU + GPU peak performance + identical NPU TOPS at +$200-500 in flagship phone pricing. For AI features specifically, the gap is small.
- vs Apple A17 Pro → A17 Pro is the 2023 iPhone 15 Pro chip — similar generation. Apple Intelligence vs Google Gemini Nano + Samsung Galaxy AI ecosystem differences.
- vs Google Tensor G4 → Google's 2024 Pixel SoC with deep Gemini Nano integration.
Overview
Flagship Android SoC. Hexagon NPU at 45 TOPS INT8. First mainstream phone NPU to run 7B-class models on-device via Qualcomm AI Hub + ONNX Runtime Mobile.
Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.
Featured in this stack
The L3 execution stacks that pick this hardware as a recommended component, with the one-line note explaining the role it plays in each.
- Stack · L3·Homelab tier·Role: Mid-tier 2023 flagship (still production-viable)Android on-device AI stack — Phi-3.5 Mini / Llama 3.2 3B via MLC LLM or Qualcomm AI Hub
Snapdragon 8 Gen 3 Hexagon NPU at 45 TOPS INT8 + 12GB+ RAM. The first widely-shipped Android NPU that runs 7B-class models on-device. Most Pixel 8 / Galaxy S24 deployments use this tier.
Specs
| VRAM | 0 GB |
| System RAM (typical) | 12 GB |
| Power draw | 5 W |
| Released | 2023 |
| Backends |
Frequently asked
Does Qualcomm Snapdragon 8 Gen 3 support CUDA?
Where next?
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify hardware specifications.