RUNLOCALAIv38
->Will it run?Best GPUCompareTroubleshootStartLearnPulseModelsHardwareToolsBench
Run check
  1. >
  2. Home
  3. /Hardware
  4. /Qualcomm Snapdragon 8 Gen 3
UNIT · QUALCOMM · MOBILE-SOC
12 GB UNIFIEDmobile·Reviewed June 2026

Qualcomm Snapdragon 8 Gen 3

QCOM · HARDWARE
Qualcomm Snapdragon 8 Gen 3

No editorial image yet — generic vendor mark shown. Credentials in spec table below.

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.

Released 2023·77 GB/s memory bandwidth
▼ CHECK CURRENT PRICE· 1 retailer
Qualcomm Snapdragon 8 Gen 3
Check on Amazon→

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.

RUNLOCALAI SCORE
See full leaderboard →
179/ 1000
DD-tier
Estimated
Throughput
18/ 500
VRAM-fit
80/ 200
Ecosystem
60/ 200
Efficiency
98/ 100

Sub-scores sum to 256 / 1000. Headline = 256 × 0.70 (Estimated-confidence discount) = 179. This is an algorithmic performance-tier score — distinct from, and often lower than, the editorial “Our verdict” below, which weighs value and real-world fit (especially for hardware we haven’t measured yet). How scoring works →

Extrapolated from 76.8 GB/s bandwidth — 6.1 tok/s estimated. No measured benchmarks yet.

WORKLOAD FIT
Try other hardware →

Plain-English: Doesn't fit modern chat models usefully.

7B chat△
Marginal
14B chat△
Marginal
32B chat✗
Doesn't fit
70B chat✗
Doesn't fit
Coding agent△
Marginal
Vision (≤8B VLM)△
Marginal
Long context (32K)✗
Doesn't fit
✓Comfortable — fits with headroom
~Tight — works, no slack
△Marginal — needs aggressive quant
✗Doesn't fit 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.

BLK · VERDICT

Our verdict

OP · Fredoline Eruo|VERIFIED JUN 18, 2026
4.5/10

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.
BLK · OVERVIEW

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.

Retailers we'd check:Amazon

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.

BLK · SPECS

Specs

VRAM0 GB
System RAM (typical)12 GB
Power draw (peak)5 W
Released2023
Backends

Frequently asked

Does Qualcomm Snapdragon 8 Gen 3 support CUDA?

Qualcomm Snapdragon 8 Gen 3 does not support CUDA. Use Vulkan-compatible tools (llama.cpp Vulkan backend) or check vendor-specific runtimes.

Where next?

Buyer guides
  • Best GPU for local AI →
  • Best laptop for local AI →
  • Best Mac for local AI →
  • Best used GPU for local AI →
Troubleshooting
  • CUDA out of memory →
  • Ollama running slowly →
  • ROCm not detected →
  • Model keeps crashing →

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify hardware specifications.

RUNLOCALAI

Independently operated catalog for local-AI hardware and software. Hand-written verdicts. Source-cited claims. Reproducible commands when we have them.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
TOOLS
  • Will it run?
  • Compare hardware
  • Cost vs cloud
  • Choose my GPU
  • Prompting kits
  • Quick answers
REF
  • All buyer guides
  • Learn local AI
  • Methodology
  • Glossary
  • Errors KB
  • Trust
EDITOR
  • About
  • Author
  • How we make money
  • Editorial policy
  • Contact
LEGAL
  • Privacy
  • Terms
  • Sitemap
MAIL · MONTHLY DIGEST
Get monthly local AI changes
Monthly recap. No spam.
DISCLOSURE

Some links on this site are affiliate links (Amazon Associates and other first-class retailers). When you buy through them, we earn a small commission at no extra cost to you. Affiliate links do not influence our verdicts — there are cards we rate highly that we don't have affiliate relationships with, and cards that sell well that we refuse to recommend. Read more →

© 2026 runlocalai.coIndependently operated
RUNLOCALAI · v38
Compare alternatives

Hardware worth comparing

The closest alternatives by price, memory bandwidth, and form factor, plus a step up and down — so you can frame the buying decision against real options.

Closest matches
Similar price, bandwidth & form factor
  • Google Tensor G4
    google · 60 GB/s
    4.8/10
  • Apple A18 Pro
    apple · 60 GB/s
    5.0/10
  • Apple A17 Pro
    apple · 51 GB/s
    4.7/10
  • AMD Ryzen AI 9 HX 370 (Strix Point)
    amd · 90 GB/s
    3.9/10
  • Apple M4 (iPad Pro)
    apple · 120 GB/s
    5.0/10
  • Qualcomm Snapdragon 8 Elite
    qualcomm · 90 GB/s
    5.3/10
Step up
More capable — more memory or a higher tier
  • Apple M4 Pro
    apple · 273 GB/s
    10.0/10
  • Apple M2 Max
    apple · 400 GB/s
    9.7/10
  • Apple M1 Max
    apple · 400 GB/s
    8.9/10
Step down
Lighter — cheaper or more constrained
  • AMD Ryzen AI 9 HX 370 (Strix Point)
    amd · 90 GB/s
    3.9/10
  • Intel Core Ultra 7 258V (Lunar Lake)
    intel · 136 GB/s
    3.8/10
  • AMD Radeon 780M (Phoenix iGPU)
    amd · 89 GB/s
    2.1/10