Acer Predator Helios 18 AI (PH18-I71-90WJ): which AI models can it run?

Estimated from the specifications below. Choose the memory size you have or plan to buy, then read the table for that size.

Specifications

Brand
Acer
Chip
Intel Core Ultra 9 290HX Plus
Processor
Intel Core Ultra 9 290HX Plus (24 cores)
Graphics
NVIDIA GeForce RTX 5090 Laptop GPU
Memory type
DDR5 SDRAM
Memory options
32 GB, 192 GB
Graphics memory
24 GB
Memory bandwidth
896 GB/s

Sources: https://www.acer.com/us-en/predator/laptops/helios/helios-18-ai/pdp/NH.U82AA.001, https://www.nvidia.com/en-us/geforce/laptops/50-series/

Acer lists 32GB standard and 192GB maximum for this part number; sizes in between are not itemised. RTX 5090 with 24GB GDDR7. GPU bandwidth from NVIDIA RTX 50 laptop page.

With 32 GB of memory

About 24 GB of it can hold a model.

ModelFitNeeds (GB)Writing speed (tokens per second)SpeedQualityBasis
Llama 3.2 3B
llama3.2:3b
Fits 5 157 to 291 Fast not measured yet Estimated
Qwen3 4B
qwen3:4b · thinks first
Fits 6 125 to 233 Fast not measured yet Estimated
Gemma 3 4B
gemma3:4b
Fits 6.7 95 to 176 Fast not measured yet Estimated
Mistral 7B v0.3
mistral:7b
Fits 7.8 71 to 132 Fast not measured yet Estimated
Llama 3.1 8B
llama3.1:8b
Fits 8.3 64 to 119 Fast not measured yet Estimated
Qwen3 8B
qwen3:8b · thinks first
Fits 8.9 60 to 112 Fast not measured yet Estimated
Gemma 3 12B
gemma3:12b
Fits 15.9 39 to 72 Fast not measured yet Estimated
DeepSeek-R1 Distill Qwen 14B
deepseek-r1:14b · thinks first
Fits 13.7 35 to 65 Fast not measured yet Estimated
Phi-4 14B
phi4:14b
Fits 13.9 34 to 64 Fast not measured yet Estimated
Qwen3 14B
qwen3:14b · thinks first
Fits 13.4 34 to 63 Fast not measured yet Estimated
gpt-oss 20B
gpt-oss:20b · thinks first
Fits 16.5 78 to 145 Fast not measured yet Estimated
Gemma 3 27B
gemma3:27b
Part of the model runs from system memory, which is much slower.
Partial offload (slow) 27.2 2.8 to 5.1 Unclear could be Slow or Moderate not measured yet Estimated
Qwen3 30B (A3B)
qwen3:30b · thinks first
Tight 22.6 92 to 170 Fast 9.3/10 Estimated
Qwen3 32B
qwen3:32b · thinks first
Part of the model runs from system memory, which is much slower.
Partial offload (slow) 26.3 2.4 to 4.4 Slow not measured yet Estimated
Llama 3.1 70B
llama3.1:70b
Part of the model runs from system memory, which is much slower.
Partial offload (slow) 51.5 1.1 to 2 Slow not measured yet Estimated
gpt-oss 120B
gpt-oss:120b
Won't fit 70.5 not known n/a not measured yet Estimated

Models marked "thinks first" can write out their reasoning before they answer, so a job takes longer than the speed alone suggests.

With 192 GB of memory

About 24 GB of it can hold a model.

ModelFitNeeds (GB)Writing speed (tokens per second)SpeedQualityBasis
Llama 3.2 3B
llama3.2:3b
Fits 5 157 to 291 Fast not measured yet Estimated
Qwen3 4B
qwen3:4b · thinks first
Fits 6 125 to 233 Fast not measured yet Estimated
Gemma 3 4B
gemma3:4b
Fits 6.7 95 to 176 Fast not measured yet Estimated
Mistral 7B v0.3
mistral:7b
Fits 7.8 71 to 132 Fast not measured yet Estimated
Llama 3.1 8B
llama3.1:8b
Fits 8.3 64 to 119 Fast not measured yet Estimated
Qwen3 8B
qwen3:8b · thinks first
Fits 8.9 60 to 112 Fast not measured yet Estimated
Gemma 3 12B
gemma3:12b
Fits 15.9 39 to 72 Fast not measured yet Estimated
DeepSeek-R1 Distill Qwen 14B
deepseek-r1:14b · thinks first
Fits 13.7 35 to 65 Fast not measured yet Estimated
Phi-4 14B
phi4:14b
Fits 13.9 34 to 64 Fast not measured yet Estimated
Qwen3 14B
qwen3:14b · thinks first
Fits 13.4 34 to 63 Fast not measured yet Estimated
gpt-oss 20B
gpt-oss:20b · thinks first
Fits 16.5 78 to 145 Fast not measured yet Estimated
Gemma 3 27B
gemma3:27b
Part of the model runs from system memory, which is much slower.
Partial offload (slow) 27.2 2.8 to 5.1 Unclear could be Slow or Moderate not measured yet Estimated
Qwen3 30B (A3B)
qwen3:30b · thinks first
Tight 22.6 92 to 170 Fast 9.3/10 Estimated
Qwen3 32B
qwen3:32b · thinks first
Part of the model runs from system memory, which is much slower.
Partial offload (slow) 26.3 2.4 to 4.4 Slow not measured yet Estimated
Llama 3.1 70B
llama3.1:70b
Part of the model runs from system memory, which is much slower.
Partial offload (slow) 51.5 1.1 to 2 Slow not measured yet Estimated
gpt-oss 120B
gpt-oss:120b · thinks first
Part of the model runs from system memory, which is much slower.
Partial offload (slow) 70.5 10 to 18 Unclear could be Moderate or Fast not measured yet Estimated

Models marked "thinks first" can write out their reasoning before they answer, so a job takes longer than the speed alone suggests.

Reported by others

Other people ran the standard llama-bench test on this chip and published the results. They are not Findra scores. The test uses a small 7-billion-parameter model, so larger models will be slower than these figures. All published benchmarks.

SetupModel and sizeWriting speed (tokens per second)Reading speed (tokens per second)Source
CUDA Llama 2 7B, Q4_0 156.5 6667 llama.cpp discussion 15013
read 2026-10-10
CUDA Llama 2 7B, Q4_0 158.1 7642 llama.cpp discussion 15013
read 2026-10-10

Reported by others, not tested by us. Results come from a public community thread; builds and settings differ between submitters.

Published chip scores

Blender Open Data publishes the median render score of its Cycles test for each chip, and PassMark publishes average CPU and 3D scores, both from results people submitted. Higher is faster. These are not Findra scores. Scores from different tests, and from different Blender versions, are not comparable with each other.

ChipTestScoreSource
NVIDIA GeForce RTX 5090 Laptop GPUBlender render, NVIDIA OptiX, Blender 5.2.08074Blender Open Data
read 2026-10-22
NVIDIA GeForce RTX 5090 Laptop GPUPassMark G3D Mark (3D and gaming)28423PassMark
read 2026-10-22

Editing, gaming, CAD and other work

Each app below publishes a minimum and a recommended system requirement. We compare them with this laptop's memory and graphics memory. We do not judge the graphics chip's class, the processor generation or the operating system, because the makers describe those in words: check the source link for the exact card, processor and system they name. Many apps and games run only on Windows or only on macOS. Integrated graphics count as below any requirement for a dedicated card. Not known means the maker does not state this laptop's graphics memory.

App32 GB192 GB
Video editing
Adobe Premiere ProRecommendedRecommended
Adobe After EffectsRecommendedRecommended
Final Cut ProRecommendedRecommended
OBS StudioMinimumMinimum
Adobe Premiere ElementsRecommendedRecommended
DaVinci ResolveMinimumMinimum
Photo editing and design
Adobe PhotoshopRecommendedRecommended
Adobe Lightroom ClassicRecommendedRecommended
Adobe IllustratorRecommendedRecommended
AffinityRecommendedRecommended
Adobe InDesignRecommendedRecommended
Capture OneRecommendedRecommended
KritaRecommendedRecommended
Clip Studio PaintRecommendedRecommended
3D, CAD and rendering
BlenderRecommendedRecommended
Autodesk AutoCADRecommendedRecommended
SOLIDWORKSRecommendedRecommended
Autodesk FusionRecommendedRecommended
Autodesk RevitMinimumMinimum
SketchUpMinimumMinimum
Autodesk MayaRecommendedRecommended
Maxon Cinema 4DRecommendedRecommended
RhinoRecommendedRecommended
KeyShot StudioRecommendedRecommended
Unreal Engine 5 editorRecommendedRecommended
Unity editorMinimumMinimum
HoudiniRecommendedRecommended
ZBrushRecommendedRecommended
Adobe Substance 3D PainterRecommendedRecommended
Autodesk 3ds MaxRecommendedRecommended
Autodesk InventorRecommendedRecommended
Autodesk Civil 3DRecommendedRecommended
ArchicadRecommendedRecommended
TwinmotionMinimumRecommended
Lumion ProRecommendedRecommended
D5 RenderRecommendedRecommended
Godot EngineRecommendedRecommended
Gaming
Cyberpunk 2077RecommendedRecommended
Baldur's Gate 3RecommendedRecommended
Elden RingRecommendedRecommended
Black Myth: WukongRecommendedRecommended
StarfieldRecommendedRecommended
Hogwarts LegacyRecommendedRecommended
Counter-Strike 2MinimumMinimum
FortniteRecommendedRecommended
Call of Duty: WarzoneRecommendedRecommended
Microsoft Flight Simulator 2024RecommendedRecommended
Alan Wake 2RecommendedRecommended
Forza Horizon 5RecommendedRecommended
Red Dead Redemption 2RecommendedRecommended
Grand Theft Auto VRecommendedRecommended
Marvel RivalsRecommendedRecommended
Helldivers 2RecommendedRecommended
Hades IIRecommendedRecommended
Stardew ValleyMinimumMinimum
Minecraft Java EditionRecommendedRecommended
Apex LegendsRecommendedRecommended
Rocket LeagueRecommendedRecommended
Dota 2MinimumMinimum
Overwatch 2RecommendedRecommended
PalworldRecommendedRecommended
Diablo IVRecommendedRecommended
Path of Exile 2RecommendedRecommended
Monster Hunter WildsRecommendedRecommended
Assassin's Creed ShadowsRecommendedRecommended
Warhammer 40,000: Space Marine 2RecommendedRecommended
Silent Hill 2RecommendedRecommended
God of War RagnarokRecommendedRecommended
The Witcher 3: Wild HuntRecommendedRecommended
Sid Meier's Civilization VIIRecommendedRecommended
Total War: Warhammer IIIRecommendedRecommended
Cities: Skylines IIRecommendedRecommended
F1 25RecommendedRecommended
EA Sports FC 25RecommendedRecommended
Forza MotorsportRecommendedRecommended
Lethal CompanyMinimumMinimum
BalatroMinimumMinimum
Vampire SurvivorsMinimumMinimum
Hollow Knight: SilksongRecommendedRecommended
SatisfactoryRecommendedRecommended
RobloxMinimumMinimum
Genshin ImpactRecommendedRecommended
AI image and video generation
InvokeAI with SD 1.5 modelsMinimumMinimum
InvokeAI with SDXL modelsMinimumMinimum
InvokeAI with FLUX.1 modelsMinimumMinimum
FooocusMinimumMinimum
LM StudioRecommendedRecommended
JanRecommendedRecommended
Music and audio production
Ableton Live 12MinimumMinimum
FL StudioMinimumMinimum
Logic ProMinimumMinimum
Pro ToolsMinimumMinimum
Steinberg CubaseMinimumMinimum
Native Instruments Kontakt 8RecommendedRecommended
Bitwig StudioMinimumMinimum
Fender Studio ProMinimumMinimum
ReasonMinimumMinimum
Traktor Pro 4MinimumMinimum
Adobe AuditionRecommendedRecommended
Software development
Android StudioRecommendedRecommended
Visual Studio 2026RecommendedRecommended
Docker DesktopMinimumMinimum
IntelliJ IDEAMinimumMinimum
Visual Studio CodeRecommendedRecommended
VMware Workstation ProRecommendedRecommended
Parallels DesktopRecommendedRecommended
Everyday work
Microsoft 365MinimumMinimum
Zoom WorkplaceRecommendedRecommended
Microsoft TeamsMinimumMinimum
Google ChromeMinimumMinimum
Windows 11MinimumMinimum

Labels follow the makers' published lists. All use cases.

Speed is the speed of writing an answer, shown as a range. Reading speed is not estimated. How the estimates work · How close they are · Back to the finder