Hailo-8 AI Processor — Benchmarks & Specs
Bottom line: how fast is the Hailo-8 AI Processor?
For local LLM inference it generates 491.0 tokens/sec running YOLOv8s at int8 under HailoRT, per Hailo Community. In MobileNet-v3 Image Classification (hw-only, batch=1, 224x224) it scores 3,697 FPS, per Hailo Model Zoo (GitHub).
Every figure above is a row in the tables below, and each row links out to the review or public benchmark database the number was taken from. SpecPicks aggregates published measurements; it does not report first-party benchmark runs.
The Hailo-8 AI Processor is an APU from the Hailo family released in 2021 from Hailo. It launched with a $200 MSRP, though street prices typically diverge meaningfully from launch pricing — see the linked product cards below for current Amazon listings. Data on this page draws on 10 synthetic benchmark results, 3 community AI inference reports, aggregated from public benchmark databases (TechPowerUp, PassMark, Geekbench, Cinebench) and the LocalLLaMA community. Read this page when shopping the Hailo-8 AI Processor, comparing it against other APUs in your build, or sizing it for a specific workload (gaming at 1080p/1440p/4K, productivity benchmarks, or local LLM inference).
AI Inference Performance
Tokens per second under each model + quantization. Higher = faster generation. Bars compare runs across the same model.
| Model | Quantization | Relative | Tokens/sec | VRAM used | Source |
|---|---|---|---|---|---|
| YOLOv8s | int8 HailoRT | 491.0 tok/s | 0.0 GB | Hailo Community 2025-09-04 | |
| YOLOv8n | int8 HailoRT | 431.0 tok/s | 0.0 GB | Hailo Community 2025-09-04 | |
| YOLOv8m (multi-stream object detection, 640x640, batch 8) | int8 HailoRT (Raspberry Pi 5) | 0.0 tok/s | 0.0 GB | Seeed Studio Wiki 2024-07-17 |
Synthetic Benchmarks
Higher is better. Bars are scaled within each benchmark family (multi-thread, single-thread, etc.) so you can compare like-with-like at a glance.
| Benchmark | Relative | Score | Source |
|---|---|---|---|
| MobileNet-v3 Image Classification (hw-only, batch=1, 224x224) | 3,697 FPS | Hailo Model Zoo (GitHub) 2024-01-01 | |
| MobileNet V1 Classification (224x224) | 3,305 FPS | Hailo AI GitHub – hailo_model_zoo 2025-03-16 | |
| ResNet V1-18 Classification (224x224) | 2,718 FPS | Hailo AI GitHub – hailo_model_zoo 2025-03-16 | |
| MobileNet-v2-1.0 Image Classification (hw-only, batch=1, 224x224) | 2,597 FPS | Hailo Model Zoo (GitHub) 2024-01-01 | |
| ResNet-v1-50 Image Classification (hw-only, batch=1, 224x224) | 1,372 FPS | Hailo Model Zoo (GitHub) 2024-01-01 | |
| ResNet V1-50 Classification (224x224, hw_only streaming) | 1,329 FPS | Hailo AI GitHub – hailo_model_zoo BENCHMARKS.rst 2025-03-16 | |
| YOLOv8n Object Detection — hailortcli benchmark (desktop PCIe, synthetic data) | 1,036 FPS | Hailo Developer Community 2025-11-27 | |
| YOLOv8n Object Detection (640x640, batch=1) | 1,036 FPS | Hailo AI GitHub – hailo_model_zoo 2025-03-16 | |
| YOLOv8n Object Detection (hw-only, batch=1, 640x640) | 1,036 FPS | Hailo Model Zoo (GitHub) 2024-01-01 | |
| SSD MobileNet V1 Detection (300x300, batch=1) | 1,015 FPS | Hailo AI GitHub – hailo_model_zoo 2025-03-16 |
Full Specifications
| ai tops | 26 |
|---|
Hailo-8 AI Processor — Frequently Asked Questions
What is the Hailo-8 AI Processor best used for?
When was the Hailo-8 AI Processor released, and what was its launch MSRP?
Where do the benchmark numbers on this page come from?
How does the Hailo-8 AI Processor compare to its predecessor?
Where can I buy the Hailo-8 AI Processor?
Buying guides that rank the Hailo-8 AI Processor's class
This page is the raw performance data. The guides below turn it into a ranked pick for a specific build.
Editorial guides covering the Hailo-8 AI Processor
In-depth SpecPicks reviews, build guides, and head-to-heads referencing this APU.
- Build a Fully Local PDF-to-Audiobook Pipeline on Jetson Orin Nano Super
- Tencent Hunyuan-MT 440MB On-Device Translator: Which Phones and SBCs Can Actually Run It?
- Raspberry Pi 5 Local LLM Server: Best Models for 8GB RAM in 2026
- Local PDF-to-Audiobook on a Raspberry Pi 5: Kokoro 82M + Qwen + llama.cpp
- Hailo-10H AI Accelerator on Raspberry Pi 5: Real Tok/s for On-Device LLMs
- Raspberry Pi 5 + AI HAT: Five Computer-Vision Projects That Actually Run in Real Time
- Jetson Orin Nano Super for ROS 2 Robotics: Build Guide + Real Latency Numbers
- Raspberry Pi 5 + Hailo-8 vs Jetson Orin Nano Super: Which Edge AI Box Wins for Vision Workloads?
- Browse all SpecPicks reviews →
More guides & deep dives from the SpecPicks archive
Browse all articles & guides →- Best Budget Gaming PC Build 2026 — ~$1,000 ($800 on Sale)
- Best 1440p Gaming GPUs in 2026
- How to Build a Windows 98 Retro PC in 2026
- Best Retro Handhelds in 2026 — From $35 to $500
- The Complete Voodoo5 5500 AGP Driver Guide (2026 Edition)
- RTX 4070 Super vs RX 7800 XT — Which to Buy in 2026
- Emulation Hardware in 2026: FPGA, Software, and Cart-Reader Ecosystems
More reviews from the SpecPicks archive
Browse all reviews →- Which Open LLMs Actually Handle Tool-Calling on an RTX 3060?
- This Switch 2 Dock Looks Exactly Like an N64 — and Holds Six Game Cards
- Ryzen 7 5800X vs Ryzen 5 5600G for Gaming and Streaming
- Best Dorm Room Gaming Setup in 2026: 5 Picks That Fit One Desk
- 4K@60fps USB Video Capture on Linux: What Works in 2026
- Steam Deck Randomly Awakens? Causes & Fixes (2026)
- RTX 3060 12GB in 2026: Is It Still a 1080p Value Champion?
- Best CPU Cooler for Ryzen 7 5800X Overclocking (2026)
- AMD Ryzen AI HALO vs RTX 3060 12GB for Local LLMs in 2026
- Modder Runs a Counter-Strike Clone at 60 FPS on the Original PSP
- Asus RTX 5060 Hits Near-MSRP on Amazon Prime — Is the Budget Blackwell Worth It?
- Best Sim Racing Wheel Setup 2026: G920 vs HORI vs TH8A
- Local PDF-to-Audiobook on a Raspberry Pi 5: Kokoro 82M + Qwen + llama.cpp
- How to run Llama 3.1 8B on Apple M3 Ultra
- SteamOS Boots on Intel Hardware: Enthusiast Hack Breaks AMD Lock-In
- How to run Llama 3.1 8B on NVIDIA GeForce RTX 5070
- AMD Revives Zen 2: Ryzen 7 4700LE in $800 RTX 3050 Prebuilts
- Pentium III Tualatin Overclocking and Slotket Build Guide: The Forgotten King of Socket 370
- Transcend CF133 CompactFlash as a Win98 Boot Drive: Speed Tests, Compatibility, and the Adapter That…
- What Fits in 12GB VRAM? RTX 3060 Local LLM Model Guide (2026)
- Best Gaming Headset Under $50 for Console + PC (2026)
- Ryzen 7 5700X vs 5800X for a 2026 Gaming and Streaming Build
- Gemma 4 31B Heretic Finetune: Can It Run on a 12GB RTX 3060?
- Ryzen AI Max 395 Laptop: Specs and AI Performance
More buying guides from SpecPicks
Browse all buying guides →- Best GPUs for Running Local LLMs in 2026
- Best PC Cases for Building in 2026
- Best External SSDs for Content Creators in 2026
- Best CPUs for Gaming in 2026
- Best NVMe External Enclosures for 2026
- Best Tools for Building and Repairing Retro PCs in 2026
- Best CPUs for Content Creators in 2026
- Best Gaming Monitors for 2026
- Best Mechanical Keyboards for Gaming in 2026
- Best CPU Coolers for 2026
- Best GPU for Running 27B-32B Local LLMs in 2026
- Best Graphics Cards for Gaming in 2026
- Best DDR5 RAM for Gaming PCs in 2026
- Best Controllers for PC Gaming in 2026
- Best Retro Gaming Consoles & Handhelds for 2026
- Best Gaming Mice for 2026
- Best 1440p 240Hz Gaming Monitors in 2026
- Best 4K Monitors for Content Creators in 2026
- Best GPUs for 4K Gaming in 2026
- Best AM5 Motherboards for 2026
- Best NVMe SSDs for Gaming in 2026