Apple MacBook Pro 16-inch (2024, M4 Pro): 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
- Apple
- Year
- 2024
- Chip
- Apple M4 Pro
- Processor
- 14-core CPU
- Graphics
- 20-core GPU
- Memory type
- unified memory
- Memory options
- 24 GB, 48 GB
- Memory bandwidth
- 273 GB/s
Sources: https://support.apple.com/en-us/121554
Apple lists 273GB/s for M4 Pro and 24GB base memory, configurable to 48GB for M4 Pro. The same page lists M4 Max options with more memory.
With 24 GB of memory
About 16.8 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 | 55 to 102 | Fast | not measured yet | Estimated |
| Qwen3 4B qwen3:4b · thinks first |
Fits | 6 | 44 to 82 | Fast | not measured yet | Estimated |
| Gemma 3 4B gemma3:4b |
Fits | 6.7 | 33 to 62 | Fast | not measured yet | Estimated |
| Mistral 7B v0.3 mistral:7b |
Fits | 7.8 | 25 to 46 | Fast | not measured yet | Estimated |
| Llama 3.1 8B llama3.1:8b |
Fits | 8.3 | 22 to 42 | Fast | not measured yet | Estimated |
| Qwen3 8B qwen3:8b · thinks first |
Fits | 8.9 | 21 to 39 | Fast | not measured yet | Estimated |
| Gemma 3 12B gemma3:12b |
Tight | 15.9 | 14 to 25 | Fast | not measured yet | Estimated |
| DeepSeek-R1 Distill Qwen 14B deepseek-r1:14b · thinks first |
Fits | 13.7 | 12 to 23 | Fast | not measured yet | Estimated |
| Phi-4 14B phi4:14b |
Fits | 13.9 | 12 to 22 | Fast | not measured yet | Estimated |
| Qwen3 14B qwen3:14b · thinks first |
Fits | 13.4 | 12 to 22 | Fast | not measured yet | Estimated |
| gpt-oss 20B gpt-oss:20b · thinks first |
Tight | 16.5 | 27 to 51 | 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 48 GB of memory
About 33.6 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 | 55 to 102 | Fast | not measured yet | Estimated |
| Qwen3 4B qwen3:4b · thinks first |
Fits | 6 | 44 to 82 | Fast | not measured yet | Estimated |
| Gemma 3 4B gemma3:4b |
Fits | 6.7 | 33 to 62 | Fast | not measured yet | Estimated |
| Mistral 7B v0.3 mistral:7b |
Fits | 7.8 | 25 to 46 | Fast | not measured yet | Estimated |
| Llama 3.1 8B llama3.1:8b |
Fits | 8.3 | 22 to 42 | Fast | not measured yet | Estimated |
| Qwen3 8B qwen3:8b · thinks first |
Fits | 8.9 | 21 to 39 | Fast | not measured yet | Estimated |
| Gemma 3 12B gemma3:12b |
Fits | 15.9 | 14 to 25 | Fast | not measured yet | Estimated |
| DeepSeek-R1 Distill Qwen 14B deepseek-r1:14b · thinks first |
Fits | 13.7 | 12 to 23 | Fast | not measured yet | Estimated |
| Phi-4 14B phi4:14b |
Fits | 13.9 | 12 to 22 | Fast | not measured yet | Estimated |
| Qwen3 14B qwen3:14b · thinks first |
Fits | 13.4 | 12 to 22 | Fast | not measured yet | Estimated |
| gpt-oss 20B gpt-oss:20b · thinks first |
Fits | 16.5 | 27 to 51 | Fast | not measured yet | Estimated |
| Gemma 3 27B gemma3:27b |
Fits | 27.2 | 6.5 to 12 | Unclear could be Moderate or Fast | not measured yet | Estimated |
| Qwen3 30B (A3B) qwen3:30b · thinks first |
Fits | 22.6 | 32 to 60 | Fast | 9.3/10 | Estimated |
| Qwen3 32B qwen3:32b · thinks first |
Fits | 26.3 | 5.5 to 10 | Unclear could be Moderate or Fast | 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.
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.
| Setup | Model and size | Writing speed (tokens per second) | Reading speed (tokens per second) | Source |
|---|---|---|---|---|
| 16 graphics cores | Llama 2 7B, Q8_0 | 30.5 | 367 | llama.cpp discussion 4167 read 2026-10-10 |
| 16 graphics cores | Llama 2 7B, Q4_0 | 49.6 | 364 | llama.cpp discussion 4167 read 2026-10-10 |
| 20 graphics cores | Llama 2 7B, Q8_0 | 30.7 | 450 | llama.cpp discussion 4167 read 2026-10-10 |
| 20 graphics cores | Llama 2 7B, Q4_0 | 50.7 | 440 | llama.cpp discussion 4167 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.
| Chip | Test | Score | Source |
|---|---|---|---|
| Apple M4 Pro | Blender render, processor, Blender 5.2.0 | 362 | Blender Open Data 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.
| App | 24 GB | 48 GB |
|---|---|---|
| Video editing | ||
| Adobe Premiere Pro | Recommended | Recommended |
| Adobe After Effects | Recommended | Recommended |
| Final Cut Pro | Recommended | Recommended |
| OBS Studio | Minimum | Minimum |
| Adobe Premiere Elements | Recommended | Recommended |
| DaVinci Resolve | Minimum | Minimum |
| Photo editing and design | ||
| Adobe Photoshop | Recommended | Recommended |
| Adobe Lightroom Classic | Recommended | Recommended |
| Adobe Illustrator | Recommended | Recommended |
| Affinity | Recommended | Recommended |
| Adobe InDesign | Recommended | Recommended |
| Capture One | Recommended | Recommended |
| Krita | Recommended | Recommended |
| Clip Studio Paint | Recommended | Recommended |
| 3D, CAD and rendering | ||
| Blender | Minimum | Recommended |
| Autodesk AutoCAD | Minimum | Recommended |
| SOLIDWORKS | Minimum | Recommended |
| Autodesk Fusion | Minimum | Recommended |
| Autodesk Revit | Minimum | Minimum |
| SketchUp | Minimum | Minimum |
| Autodesk Maya | Recommended | Recommended |
| Maxon Cinema 4D | Recommended | Recommended |
| Rhino | Recommended | Recommended |
| KeyShot Studio | Recommended | Recommended |
| Unreal Engine 5 editor | Below minimum | Recommended |
| Unity editor | Minimum | Minimum |
| Houdini | Minimum | Recommended |
| ZBrush | Recommended | Recommended |
| Adobe Substance 3D Painter | Minimum | Recommended |
| Autodesk 3ds Max | Recommended | Recommended |
| Autodesk Inventor | Minimum | Recommended |
| Autodesk Civil 3D | Minimum | Recommended |
| Archicad | Recommended | Recommended |
| Twinmotion | Minimum | Minimum |
| Lumion Pro | Minimum | Recommended |
| D5 Render | Minimum | Recommended |
| Godot Engine | Recommended | Recommended |
| Gaming | ||
| Cyberpunk 2077 | Recommended | Recommended |
| Baldur's Gate 3 | Recommended | Recommended |
| Elden Ring | Recommended | Recommended |
| Black Myth: Wukong | Recommended | Recommended |
| Starfield | Recommended | Recommended |
| Hogwarts Legacy | Recommended | Recommended |
| Counter-Strike 2 | Minimum | Minimum |
| Fortnite | Recommended | Recommended |
| Call of Duty: Warzone | Recommended | Recommended |
| Microsoft Flight Simulator 2024 | Minimum | Recommended |
| Alan Wake 2 | Recommended | Recommended |
| Forza Horizon 5 | Recommended | Recommended |
| Red Dead Redemption 2 | Recommended | Recommended |
| Grand Theft Auto V | Recommended | Recommended |
| Marvel Rivals | Recommended | Recommended |
| Helldivers 2 | Recommended | Recommended |
| Hades II | Recommended | Recommended |
| Stardew Valley | Minimum | Minimum |
| Minecraft Java Edition | Recommended | Recommended |
| Apex Legends | Recommended | Recommended |
| Rocket League | Recommended | Recommended |
| Dota 2 | Minimum | Minimum |
| Overwatch 2 | Recommended | Recommended |
| Palworld | Minimum | Recommended |
| Diablo IV | Recommended | Recommended |
| Path of Exile 2 | Recommended | Recommended |
| Monster Hunter Wilds | Recommended | Recommended |
| Assassin's Creed Shadows | Recommended | Recommended |
| Warhammer 40,000: Space Marine 2 | Recommended | Recommended |
| Silent Hill 2 | Recommended | Recommended |
| God of War Ragnarok | Recommended | Recommended |
| The Witcher 3: Wild Hunt | Recommended | Recommended |
| Sid Meier's Civilization VII | Recommended | Recommended |
| Total War: Warhammer III | Recommended | Recommended |
| Cities: Skylines II | Recommended | Recommended |
| F1 25 | Recommended | Recommended |
| EA Sports FC 25 | Recommended | Recommended |
| Forza Motorsport | Recommended | Recommended |
| Lethal Company | Minimum | Minimum |
| Balatro | Minimum | Minimum |
| Vampire Survivors | Minimum | Minimum |
| Hollow Knight: Silksong | Recommended | Recommended |
| Satisfactory | Recommended | Recommended |
| Roblox | Minimum | Minimum |
| Genshin Impact | Recommended | Recommended |
| AI image and video generation | ||
| InvokeAI with SD 1.5 models | Minimum | Minimum |
| InvokeAI with SDXL models | Minimum | Minimum |
| InvokeAI with FLUX.1 models | Below minimum | Minimum |
| Fooocus | Minimum | Minimum |
| LM Studio | Recommended | Recommended |
| Jan | Recommended | Recommended |
| Music and audio production | ||
| Ableton Live 12 | Minimum | Minimum |
| FL Studio | Minimum | Minimum |
| Logic Pro | Minimum | Minimum |
| Pro Tools | Minimum | Minimum |
| Steinberg Cubase | Minimum | Minimum |
| Native Instruments Kontakt 8 | Recommended | Recommended |
| Bitwig Studio | Minimum | Minimum |
| Fender Studio Pro | Minimum | Minimum |
| Reason | Minimum | Minimum |
| Traktor Pro 4 | Minimum | Minimum |
| Adobe Audition | Recommended | Recommended |
| Software development | ||
| Android Studio | Minimum | Recommended |
| Visual Studio 2026 | Recommended | Recommended |
| Docker Desktop | Minimum | Minimum |
| IntelliJ IDEA | Minimum | Minimum |
| Visual Studio Code | Recommended | Recommended |
| VMware Workstation Pro | Recommended | Recommended |
| Parallels Desktop | Recommended | Recommended |
| Everyday work | ||
| Microsoft 365 | Minimum | Minimum |
| Zoom Workplace | Recommended | Recommended |
| Microsoft Teams | Minimum | Minimum |
| Google Chrome | Minimum | Minimum |
| Windows 11 | 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