HP EliteBook 8 G1a 14 inch Notebook AI PC: 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: HP
Chip: AMD Ryzen 7 PRO 250/249, Ryzen 7 250/249 or Ryzen 5 PRO 224/230, Ryzen 5 224/230
Processor: Ryzen 7 (8 cores) or Ryzen 5 (6 cores)
Graphics: AMD Radeon Graphics (integrated)
Memory type: DDR5-5600 SODIMM (2 slots)
Memory options: 8 GB, 16 GB, 24 GB, 32 GB, 64 GB
Memory bandwidth: 89.6 GB/s

Sources: https://h20195.www2.hp.com/v2/getpdf.aspx/c09120198.pdf

Derived: HP prints dual channel memory but not GB/s; 128 bits (two 64-bit channels) x 5600 MT/s / 8 / 1000 = 89.6GB/s peak. Needs two modules fitted; the page marks dual channel as optional. QuickSpecs lists 8, 16, 24, 32 and 64GB DDR5-5600. This sheet names the graphics only as AMD Radeon Graphics.

With 8 GB of memory

About 4 GB of it can hold a model.

Model	Fit	Needs (GB)	Writing speed (tokens per second)	Speed	Quality	Basis
Llama 3.2 3B llama3.2:3b	Won't fit	5	not known	n/a	not measured yet	Estimated
Qwen3 4B qwen3:4b	Won't fit	6	not known	n/a	not measured yet	Estimated
Gemma 3 4B gemma3:4b	Won't fit	6.7	not known	n/a	not measured yet	Estimated
Mistral 7B v0.3 mistral:7b	Won't fit	7.8	not known	n/a	not measured yet	Estimated
Llama 3.1 8B llama3.1:8b	Won't fit	8.3	not known	n/a	not measured yet	Estimated
Qwen3 8B qwen3:8b	Won't fit	8.9	not known	n/a	not measured yet	Estimated
Gemma 3 12B gemma3:12b	Won't fit	15.9	not known	n/a	not measured yet	Estimated
DeepSeek-R1 Distill Qwen 14B deepseek-r1:14b	Won't fit	13.7	not known	n/a	not measured yet	Estimated
Phi-4 14B phi4:14b	Won't fit	13.9	not known	n/a	not measured yet	Estimated
Qwen3 14B qwen3:14b	Won't fit	13.4	not known	n/a	not measured yet	Estimated
gpt-oss 20B gpt-oss:20b	Won't fit	16.5	not known	n/a	not measured yet	Estimated
Gemma 3 27B gemma3:27b	Won't fit	27.2	not known	n/a	not measured yet	Estimated
Qwen3 30B (A3B) qwen3:30b	Won't fit	22.6	not known	n/a	9.3/10	Estimated
Qwen3 32B qwen3:32b	Won't fit	26.3	not known	n/a	not measured yet	Estimated
Llama 3.1 70B llama3.1:70b	Won't fit	51.5	not known	n/a	not measured yet	Estimated
gpt-oss 120B gpt-oss:120b	Won't fit	70.5	not known	n/a	not measured yet	Estimated

With 16 GB of memory

About 12 GB of it can hold a model.

Model	Fit	Needs (GB)	Writing speed (tokens per second)	Speed	Quality	Basis
Llama 3.2 3B llama3.2:3b	Fits	5	16 to 29	Fast	not measured yet	Estimated
Qwen3 4B qwen3:4b · thinks first	Fits	6	13 to 23	Fast	not measured yet	Estimated
Gemma 3 4B gemma3:4b	Fits	6.7	9.5 to 18	Unclear could be Moderate or Fast	not measured yet	Estimated
Mistral 7B v0.3 mistral:7b	Fits	7.8	7.1 to 13	Unclear could be Moderate or Fast	not measured yet	Estimated
Llama 3.1 8B llama3.1:8b	Fits	8.3	6.4 to 12	Unclear could be Moderate or Fast	not measured yet	Estimated
Qwen3 8B qwen3:8b · thinks first	Fits	8.9	6 to 11	Unclear could be Moderate or Fast	not measured yet	Estimated
Gemma 3 12B gemma3:12b	Won't fit	15.9	not known	n/a	not measured yet	Estimated
DeepSeek-R1 Distill Qwen 14B deepseek-r1:14b	Won't fit	13.7	not known	n/a	not measured yet	Estimated
Phi-4 14B phi4:14b	Won't fit	13.9	not known	n/a	not measured yet	Estimated
Qwen3 14B qwen3:14b	Won't fit	13.4	not known	n/a	not measured yet	Estimated
gpt-oss 20B gpt-oss:20b	Won't fit	16.5	not known	n/a	not measured yet	Estimated
Gemma 3 27B gemma3:27b	Won't fit	27.2	not known	n/a	not measured yet	Estimated
Qwen3 30B (A3B) qwen3:30b	Won't fit	22.6	not known	n/a	9.3/10	Estimated
Qwen3 32B qwen3:32b	Won't fit	26.3	not known	n/a	not measured yet	Estimated
Llama 3.1 70B llama3.1:70b	Won't fit	51.5	not known	n/a	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 24 GB of memory

About 20 GB of it can hold a model.

Model	Fit	Needs (GB)	Writing speed (tokens per second)	Speed	Quality	Basis
Llama 3.2 3B llama3.2:3b	Fits	5	16 to 29	Fast	not measured yet	Estimated
Qwen3 4B qwen3:4b · thinks first	Fits	6	13 to 23	Fast	not measured yet	Estimated
Gemma 3 4B gemma3:4b	Fits	6.7	9.5 to 18	Unclear could be Moderate or Fast	not measured yet	Estimated
Mistral 7B v0.3 mistral:7b	Fits	7.8	7.1 to 13	Unclear could be Moderate or Fast	not measured yet	Estimated
Llama 3.1 8B llama3.1:8b	Fits	8.3	6.4 to 12	Unclear could be Moderate or Fast	not measured yet	Estimated
Qwen3 8B qwen3:8b · thinks first	Fits	8.9	6 to 11	Unclear could be Moderate or Fast	not measured yet	Estimated
Gemma 3 12B gemma3:12b	Fits	15.9	3.9 to 7.2	Unclear could be Slow or Moderate	not measured yet	Estimated
DeepSeek-R1 Distill Qwen 14B deepseek-r1:14b · thinks first	Fits	13.7	3.5 to 6.5	Unclear could be Slow or Moderate	not measured yet	Estimated
Phi-4 14B phi4:14b	Fits	13.9	3.4 to 6.4	Unclear could be Slow or Moderate	not measured yet	Estimated
Qwen3 14B qwen3:14b · thinks first	Fits	13.4	3.4 to 6.3	Unclear could be Slow or Moderate	not measured yet	Estimated
gpt-oss 20B gpt-oss:20b · thinks first	Fits	16.5	7.8 to 14	Unclear could be Moderate or Fast	not measured yet	Estimated
Gemma 3 27B gemma3:27b	Won't fit	27.2	not known	n/a	not measured yet	Estimated
Qwen3 30B (A3B) qwen3:30b	Won't fit	22.6	not known	n/a	9.3/10	Estimated
Qwen3 32B qwen3:32b	Won't fit	26.3	not known	n/a	not measured yet	Estimated
Llama 3.1 70B llama3.1:70b	Won't fit	51.5	not known	n/a	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 32 GB of memory

About 28 GB of it can hold a model.

Model	Fit	Needs (GB)	Writing speed (tokens per second)	Speed	Quality	Basis
Llama 3.2 3B llama3.2:3b	Fits	5	16 to 29	Fast	not measured yet	Estimated
Qwen3 4B qwen3:4b · thinks first	Fits	6	13 to 23	Fast	not measured yet	Estimated
Gemma 3 4B gemma3:4b	Fits	6.7	9.5 to 18	Unclear could be Moderate or Fast	not measured yet	Estimated
Mistral 7B v0.3 mistral:7b	Fits	7.8	7.1 to 13	Unclear could be Moderate or Fast	not measured yet	Estimated
Llama 3.1 8B llama3.1:8b	Fits	8.3	6.4 to 12	Unclear could be Moderate or Fast	not measured yet	Estimated
Qwen3 8B qwen3:8b · thinks first	Fits	8.9	6 to 11	Unclear could be Moderate or Fast	not measured yet	Estimated
Gemma 3 12B gemma3:12b	Fits	15.9	3.9 to 7.2	Unclear could be Slow or Moderate	not measured yet	Estimated
DeepSeek-R1 Distill Qwen 14B deepseek-r1:14b · thinks first	Fits	13.7	3.5 to 6.5	Unclear could be Slow or Moderate	not measured yet	Estimated
Phi-4 14B phi4:14b	Fits	13.9	3.4 to 6.4	Unclear could be Slow or Moderate	not measured yet	Estimated
Qwen3 14B qwen3:14b · thinks first	Fits	13.4	3.4 to 6.3	Unclear could be Slow or Moderate	not measured yet	Estimated
gpt-oss 20B gpt-oss:20b · thinks first	Fits	16.5	7.8 to 14	Unclear could be Moderate or Fast	not measured yet	Estimated
Gemma 3 27B gemma3:27b	Tight	27.2	1.8 to 3.4	Slow	not measured yet	Estimated
Qwen3 30B (A3B) qwen3:30b · thinks first	Fits	22.6	9.2 to 17	Unclear could be Moderate or Fast	9.3/10	Estimated
Qwen3 32B qwen3:32b · thinks first	Tight	26.3	1.6 to 2.9	Slow	not measured yet	Estimated
Llama 3.1 70B llama3.1:70b	Won't fit	51.5	not known	n/a	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 64 GB of memory

About 60 GB of it can hold a model.

Model	Fit	Needs (GB)	Writing speed (tokens per second)	Speed	Quality	Basis
Llama 3.2 3B llama3.2:3b	Fits	5	16 to 29	Fast	not measured yet	Estimated
Qwen3 4B qwen3:4b · thinks first	Fits	6	13 to 23	Fast	not measured yet	Estimated
Gemma 3 4B gemma3:4b	Fits	6.7	9.5 to 18	Unclear could be Moderate or Fast	not measured yet	Estimated
Mistral 7B v0.3 mistral:7b	Fits	7.8	7.1 to 13	Unclear could be Moderate or Fast	not measured yet	Estimated
Llama 3.1 8B llama3.1:8b	Fits	8.3	6.4 to 12	Unclear could be Moderate or Fast	not measured yet	Estimated
Qwen3 8B qwen3:8b · thinks first	Fits	8.9	6 to 11	Unclear could be Moderate or Fast	not measured yet	Estimated
Gemma 3 12B gemma3:12b	Fits	15.9	3.9 to 7.2	Unclear could be Slow or Moderate	not measured yet	Estimated
DeepSeek-R1 Distill Qwen 14B deepseek-r1:14b · thinks first	Fits	13.7	3.5 to 6.5	Unclear could be Slow or Moderate	not measured yet	Estimated
Phi-4 14B phi4:14b	Fits	13.9	3.4 to 6.4	Unclear could be Slow or Moderate	not measured yet	Estimated
Qwen3 14B qwen3:14b · thinks first	Fits	13.4	3.4 to 6.3	Unclear could be Slow or Moderate	not measured yet	Estimated
gpt-oss 20B gpt-oss:20b · thinks first	Fits	16.5	7.8 to 14	Unclear could be Moderate or Fast	not measured yet	Estimated
Gemma 3 27B gemma3:27b	Fits	27.2	1.8 to 3.4	Slow	not measured yet	Estimated
Qwen3 30B (A3B) qwen3:30b · thinks first	Fits	22.6	9.2 to 17	Unclear could be Moderate or Fast	9.3/10	Estimated
Qwen3 32B qwen3:32b · thinks first	Fits	26.3	1.6 to 2.9	Slow	not measured yet	Estimated
Llama 3.1 70B llama3.1:70b	Fits	51.5	0.7 to 1.4	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.

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.

App	8 GB	16 GB	24 GB	32 GB	64 GB
Video editing
Adobe Premiere Pro	Minimum	Recommended	Recommended	Recommended	Recommended
Adobe After Effects	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Final Cut Pro	Minimum	Recommended	Recommended	Recommended	Recommended
OBS Studio	Minimum	Minimum	Minimum	Minimum	Minimum
Adobe Premiere Elements	Minimum	Recommended	Recommended	Recommended	Recommended
DaVinci Resolve	Below minimum	Minimum	Minimum	Minimum	Minimum
Photo editing and design
Adobe Photoshop	Minimum	Recommended	Recommended	Recommended	Recommended
Adobe Lightroom Classic	Minimum	Recommended	Recommended	Recommended	Recommended
Adobe Illustrator	Minimum	Recommended	Recommended	Recommended	Recommended
Affinity	Recommended	Recommended	Recommended	Recommended	Recommended
Adobe InDesign	Minimum	Recommended	Recommended	Recommended	Recommended
Capture One	Minimum	Minimum	Minimum	Minimum	Minimum
Krita	Minimum	Recommended	Recommended	Recommended	Recommended
Clip Studio Paint	Recommended	Recommended	Recommended	Recommended	Recommended
3D, CAD and rendering
Blender	Minimum	Minimum	Minimum	Recommended	Recommended
Autodesk AutoCAD	Below minimum	Minimum	Minimum	Minimum	Minimum
SOLIDWORKS	Below minimum	Minimum	Minimum	Recommended	Recommended
Autodesk Fusion	Minimum	Minimum	Minimum	Recommended	Recommended
Autodesk Revit	Below minimum	Minimum	Minimum	Minimum	Minimum
SketchUp	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Autodesk Maya	Minimum	Recommended	Recommended	Recommended	Recommended
Maxon Cinema 4D	Recommended	Recommended	Recommended	Recommended	Recommended
Rhino	Recommended	Recommended	Recommended	Recommended	Recommended
KeyShot Studio	Minimum	Recommended	Recommended	Recommended	Recommended
Unreal Engine 5 editor	Below minimum	Below minimum	Below minimum	Recommended	Recommended
Unity editor	Minimum	Minimum	Minimum	Minimum	Minimum
Houdini	Below minimum	Minimum	Minimum	Recommended	Recommended
ZBrush	Recommended	Recommended	Recommended	Recommended	Recommended
Adobe Substance 3D Painter	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Autodesk 3ds Max	Recommended	Recommended	Recommended	Recommended	Recommended
Autodesk Inventor	Below minimum	Minimum	Minimum	Minimum	Minimum
Autodesk Civil 3D	Below minimum	Minimum	Minimum	Minimum	Minimum
Archicad	Minimum	Recommended	Recommended	Recommended	Recommended
Twinmotion	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Lumion Pro	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
D5 Render	Minimum	Minimum	Minimum	Recommended	Recommended
Godot Engine	Minimum	Minimum	Minimum	Minimum	Minimum
Gaming
Cyberpunk 2077	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Baldur's Gate 3	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Elden Ring	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Black Myth: Wukong	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Starfield	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Hogwarts Legacy	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Counter-Strike 2	Minimum	Minimum	Minimum	Minimum	Minimum
Fortnite	Minimum	Minimum	Minimum	Minimum	Minimum
Call of Duty: Warzone	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Microsoft Flight Simulator 2024	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Alan Wake 2	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Forza Horizon 5	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Red Dead Redemption 2	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Grand Theft Auto V	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Marvel Rivals	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Helldivers 2	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Hades II	Minimum	Minimum	Minimum	Minimum	Minimum
Stardew Valley	Minimum	Minimum	Minimum	Minimum	Minimum
Minecraft Java Edition	Below minimum	Minimum	Minimum	Minimum	Minimum
Apex Legends	Minimum	Minimum	Minimum	Minimum	Minimum
Rocket League	Minimum	Minimum	Minimum	Minimum	Minimum
Dota 2	Minimum	Minimum	Minimum	Minimum	Minimum
Overwatch 2	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Palworld	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Diablo IV	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Path of Exile 2	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Monster Hunter Wilds	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Assassin's Creed Shadows	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Warhammer 40,000: Space Marine 2	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Silent Hill 2	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
God of War Ragnarok	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
The Witcher 3: Wild Hunt	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Sid Meier's Civilization VII	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Total War: Warhammer III	Recommended	Recommended	Recommended	Recommended	Recommended
Cities: Skylines II	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
F1 25	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
EA Sports FC 25	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Forza Motorsport	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Lethal Company	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Balatro	Minimum	Minimum	Minimum	Minimum	Minimum
Vampire Survivors	Minimum	Minimum	Minimum	Minimum	Minimum
Hollow Knight: Silksong	Minimum	Minimum	Minimum	Minimum	Minimum
Satisfactory	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Roblox	Minimum	Minimum	Minimum	Minimum	Minimum
Genshin Impact	Minimum	Minimum	Minimum	Minimum	Minimum
AI image and video generation
InvokeAI with SD 1.5 models	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
InvokeAI with SDXL models	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
InvokeAI with FLUX.1 models	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Fooocus	Minimum	Minimum	Minimum	Minimum	Minimum
LM Studio	Below minimum	Below minimum	Below minimum	Below minimum	Below minimum
Jan	Minimum	Recommended	Recommended	Recommended	Recommended
Music and audio production
Ableton Live 12	Minimum	Minimum	Minimum	Minimum	Minimum
FL Studio	Minimum	Minimum	Minimum	Minimum	Minimum
Logic Pro	Minimum	Minimum	Minimum	Minimum	Minimum
Pro Tools	Below minimum	Minimum	Minimum	Minimum	Minimum
Steinberg Cubase	Minimum	Minimum	Minimum	Minimum	Minimum
Native Instruments Kontakt 8	Recommended	Recommended	Recommended	Recommended	Recommended
Bitwig Studio	Minimum	Minimum	Minimum	Minimum	Minimum
Fender Studio Pro	Minimum	Minimum	Minimum	Minimum	Minimum
Reason	Minimum	Minimum	Minimum	Minimum	Minimum
Traktor Pro 4	Minimum	Minimum	Minimum	Minimum	Minimum
Adobe Audition	Minimum	Recommended	Recommended	Recommended	Recommended
Software development
Android Studio	Minimum	Minimum	Minimum	Recommended	Recommended
Visual Studio 2026	Minimum	Recommended	Recommended	Recommended	Recommended
Docker Desktop	Minimum	Minimum	Minimum	Minimum	Minimum
IntelliJ IDEA	Minimum	Minimum	Minimum	Minimum	Minimum
Visual Studio Code	Recommended	Recommended	Recommended	Recommended	Recommended
VMware Workstation Pro	Recommended	Recommended	Recommended	Recommended	Recommended
Parallels Desktop	Minimum	Recommended	Recommended	Recommended	Recommended
Everyday work
Microsoft 365	Minimum	Minimum	Minimum	Minimum	Minimum
Zoom Workplace	Minimum	Recommended	Recommended	Recommended	Recommended
Microsoft Teams	Minimum	Minimum	Minimum	Minimum	Minimum
Google Chrome	Minimum	Minimum	Minimum	Minimum	Minimum
Windows 11	Minimum	Minimum	Minimum	Minimum	Minimum

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