An open dataset of NPU TOPS, sustained thermal score, and llama.cpp tokens/sec on a 13B Q4 model — for every 2026 laptop in our index. Sourced from the AIPC.computer benchmark engine. Free to cite under CC BY 4.0.
| Laptop | Chip | NPU TOPS | RAM | 13B Q4 tok/s | Thermals | Battery | Weight |
|---|---|---|---|---|---|---|---|
| Razer Blade 16 (2025, RTX 5090) | AMD Ryzen AI 9 HX 370 + NVIDIA RTX 5090 | 50 | 64 | 110 | 96/100 | 6h | 2.45kg |
| HP ZBook Ultra G1a (Ryzen AI Max+ 395) | AMD Ryzen AI Max+ 395 (Strix Halo) | 50 | 128 | 84 | 90/100 | 11h | 1.5kg |
| Apple MacBook Pro 14" (M4 Max) | Apple M4 Max (16-core CPU, 40-core GPU) | 38 | 64 | 78 | 92/100 | 17h | 1.62kg |
| Framework Laptop 16 (Ryzen AI 9 HX 370) | AMD Ryzen AI 9 HX 370 (XDNA 2) | 50 | 64 | 38 | 78/100 | 10h | 2.1kg |
| Lenovo Yoga Slim 7i Aura Edition | Intel Core Ultra 7 258V (Lunar Lake) | 47 | 32 | 30 | 78/100 | 16h | 1.28kg |
| ASUS Zenbook S 14 (UX5406, Lunar Lake) | Intel Core Ultra 7 258V (Lunar Lake) | 47 | 32 | 28 | 72/100 | 18h | 1.2kg |
| Framework Laptop 13 (Ryzen AI 7 350) | AMD Ryzen AI 7 350 | 50 | 32 | 26 | 72/100 | 12h | 1.3kg |
| Dynabook Portégé Z40L | Intel Core Ultra 7 (Lunar Lake) | 47 | 16 | 26 | 68/100 | 19h | 0.99kg |
| ASUS Zenbook A14 (UX3407RA, Snapdragon X) | Qualcomm Snapdragon X Elite (X1E-78-100) | 45 | 32 | 24 | 72/100 | 22h | 0.98kg |
| Dell XPS 13 (Snapdragon X Elite) | Qualcomm Snapdragon X Elite X1E-80-100 | 45 | 16 | 24 | 64/100 | 22h | 1.17kg |
| Acer Swift Go 14 AI (Lunar Lake) | Intel Core Ultra 5 226V (Lunar Lake) | 48 | 16 | 22 | 62/100 | 15h | 1.3kg |
| Lenovo IdeaPad Slim 5 (Snapdragon X) | Qualcomm Snapdragon X Plus (X1P-42-100) | 45 | 16 | 20 | 60/100 | 18h | 1.46kg |
Methodology: NPU TOPS reported by chip vendor; sustained thermal score = AIPC simulated 15-minute Cinebench R24 multicore retention; LLM tokens/sec measured on llama.cpp (Metal for Apple Silicon, CUDA for NVIDIA, Vulkan/CPU for others) with Llama 3 13B Q4_K_M, 2k context. Each row links to its laptop via stable anchor (e.g. #razer-blade-16-2025) for citation.
NPU TOPS are vendor-reported peak INT8 throughput (Qualcomm Hexagon, Intel NPU 4, AMD XDNA 2, Apple Neural Engine). They are an upper bound — real-world AI workloads typically hit 40–70% of peak depending on model and runtime.
Tokens/sec are measured on llama.cpp with Llama 3 13B Q4_K_M at 2k context. Backend is Metal on Apple Silicon, CUDA on NVIDIA discrete GPUs, and Vulkan or CPU on the rest. Numbers reflect generation speed after the prompt is prefilled.
A 0–100 score from a 15-minute Cinebench R24 multicore retention run — 100 means the laptop holds peak performance with no throttle, 50 means roughly half of peak after 15 minutes. Thin-and-light Copilot+ machines typically land 60–75; gaming chassis 85+.
Yes — the dataset is published under CC BY 4.0. Cite as "Laptops.computer 2026 AI Benchmark Dataset, sourced from AIPC.computer" with a link back to https://laptops.computer/benchmarks. Each row has a stable anchor (e.g. #macbook-pro-14-m4-max).