Apple M1 Ultra 20 Core — Benchmarks & Specs
Bottom line: how fast is the Apple M1 Ultra 20 Core?
At 4K (Ultra), the Apple M1 Ultra 20 Core averages 60 fps in Baldur's Gate 3, per MacGamingDB. For local LLM inference it generates 74.9 tokens/sec running llama:7b at q4_0 under llama.cpp, per llama.cpp GitHub Discussion #4167. In PassMark CPU Mark it scores 41,392 points, per PassMark Software.
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 Apple M1 Ultra 20 Core is a processor from Apple. Data on this page draws on 10 synthetic benchmark results, 10 community AI inference reports, 3 measured game frame-rate results, aggregated from public benchmark databases (TechPowerUp, PassMark, Geekbench, Cinebench) and the LocalLLaMA community. Read this page when shopping the Apple M1 Ultra 20 Core, comparing it against other processors in your build, or sizing it for a specific workload (gaming at 1080p/1440p/4K, productivity benchmarks, or local LLM inference).
Gaming Performance (measured FPS)
Average and 1% low frame rates by game, resolution, and quality preset. Bars are scaled against the fastest result on this page.
| Game | Resolution | Settings | Relative | Avg FPS | 1% low | Source |
|---|---|---|---|---|---|---|
| Shadow of the Tomb Raider | 1080p | Highest | 108 fps | — | Notebookcheck 2022-03-18 | |
| Shadow of the Tomb Raider | 1080p | Ultra | 100 fps | 80 fps | Mac Expert Guide 2022-04-14 | |
| Baldur's Gate 3 | 4K | Ultra | 60 fps | — | MacGamingDB 2023-09-22 |
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 |
|---|---|---|---|---|---|
| llama:7b | q4_0 llama.cpp | 74.9 tok/s | — | llama.cpp GitHub Discussion #4167 2023-10-01 | |
| llama-1:7b | q4_0 llama.cpp | 74.9 tok/s | — | llama.cpp GitHub Discussion #4167 2023-11-21 | |
| llama-2-7b | q4_0 llama.cpp | 74.9 tok/s | — | llama.cpp GitHub Discussion #4167 2023-11-21 | |
| llama:7b | q8_0 llama.cpp | 55.7 tok/s | — | llama.cpp GitHub Discussion #4167 2023-10-01 | |
| llama-2-7b | q8_0 llama.cpp | 55.7 tok/s | — | llama.cpp GitHub Discussion #4167 2023-11-21 | |
| llama-1:7b | q8_0 llama.cpp | 55.7 tok/s | — | llama.cpp GitHub Discussion #4167 2023-11-21 | |
| llama-1:7b | FP16 llama.cpp | 33.9 tok/s | — | llama.cpp GitHub Discussion #4167 2023-11-21 | |
| llama-2-7b | FP16 llama.cpp | 33.9 tok/s | — | llama.cpp GitHub Discussion #4167 2023-11-21 | |
| llama:7b | FP16 llama.cpp | 33.9 tok/s | — | llama.cpp GitHub Discussion #4167 2023-10-01 | |
| llama3.1:70b | q4_K_M ollama | 8.5 tok/s | — | kunalganglani.com LLM Benchmarks 2024-09-01 |
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 |
|---|---|---|---|
| PassMark CPU Mark | 41,392 points | PassMark Software 2026-09-04 | |
| PassMark CPU Mark | 41,380 points | PassMark 2022-04-02 | |
| Cinebench R23 multi | 24,210 points | AppleInsider 2022-03-22 | |
| Geekbench 6 multi | 18,458 points | CpuTronic 2025-03-01 | |
| Geekbench 6 multi | 18,457 points | Geekbench Browser 2023-06-01 | |
| PassMark Single Thread | 3,860 points | PassMark Software 2026-09-04 | |
| PassMark Single Thread | 3,860 points | PassMark 2026-07-02 | |
| Geekbench 6 single | 2,398 points | CpuTronic 2025-03-01 | |
| Geekbench 6 single | 2,398 points | Geekbench Browser 2023-06-01 | |
| Cinebench R23 single | 1,535 points | AppleInsider 2022-03-22 |
Apple M1 Ultra 20 Core — Frequently Asked Questions
What is the Apple M1 Ultra 20 Core best used for?
When was the Apple M1 Ultra 20 Core released, and what was its launch MSRP?
Where do the benchmark numbers on this page come from?
How does the Apple M1 Ultra 20 Core compare to its predecessor?
Where can I buy the Apple M1 Ultra 20 Core?
Buying guides that rank the Apple M1 Ultra 20 Core'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 Apple M1 Ultra 20 Core
In-depth SpecPicks reviews, build guides, and head-to-heads referencing this processor.
- Arc B580 12GB vs RTX 3060 12GB: Which 12GB Card for 1440p in 2026?
- Best Wired Gear for Tournament-Legal LAN Play in 2026
- One Monitor, Two PCs: Monitor KVM vs Dual-Input for a Gaming Rig and AI Box
- Alien: Isolation on Steam Deck: Best Settings for 2025
- GTX 1660 VRAM: Why 8GB Doesn't Exist (Real Specs)
- The Greatest GPU Awards: A Decade of Standout Cards
- Noctua NH-U12S vs Corsair H150i vs Kraken M22 on a 24/7 Ryzen 7 5800X Host
- Best Gear for Online D&D and Virtual Tabletop Nights in 2026
- Browse all SpecPicks reviews →
More guides & deep dives from the SpecPicks archive
Browse all articles & guides →- Emulation Hardware in 2026: FPGA, Software, and Cart-Reader Ecosystems
- RTX 4070 Super vs RX 7800 XT — Which to Buy in 2026
- The Complete Voodoo5 5500 AGP Driver Guide (2026 Edition)
- Best 1440p Gaming GPUs in 2026
- Best Budget Gaming PC Build 2026 — ~$1,000 ($800 on Sale)
- Best Retro Handhelds in 2026 — From $35 to $500
- How to Build a Windows 98 Retro PC in 2026
More reviews from the SpecPicks archive
Browse all reviews →- Best Controller for RetroPie & Pi Emulation: SN30 Pro vs DualSense
- Abit BP6 Dual Celeron 366 Build Guide: The Legendary $200 SMP Workstation in 2026
- Intel Arc Pro B70 Linux Gaming Performance 2026
- RTX 3060 12GB: Ollama vs llama.cpp vs vLLM Token Speed (2026)
- Best Upgrades for a DDR4 Gaming PC in 2026
- Best Gaming Mouse Pad for Esports and Productivity (2026)
- Best Budget GPU for Running Llama 70B Locally: RTX 3060 12GB Stacked
- Best CPU Cooler for a Ryzen 5800X Under PBO + Manual Overclock in 2026
- Ollama vs llama.cpp vs vLLM on the RTX 3060 12GB
- Intel Arc Pro B60 Gaming Performance: 2025 Benchmarks
- How to run Qwen 3 32B on Apple M4 Pro
- Claude Opus 4.8 Tops GPT-5.5: What Runs Local on a 12GB GPU
- Blue Yeti vs HyperX QuadCast 2 S: Best Streaming Mic 2026
- DeepSeek V4 Pro at $0.04 a Task: When Local Still Beats the Cloud
- Best Wireless Streaming Microphones for Twitch in 2026
- Count Anything Runs Locally on a 12GB GPU: Object-Counting AI on the RTX 3060
- Renting AI Compute vs Running It Home: The RTX 3060 Math
- Pi Pico Puts Bluetooth Keyboards on the I2C Bus
- GameSir G7 SE vs 8BitDo Pro 2: Best Wired-vs-Wireless PC Controller
- Claude Fable 5 Beats GPT-5.5 by 13 Points: The Local-LLM Reality Check
- Ryzen 7 5800X vs 5700X vs 5600G for a Budget Local-LLM Rig
- Sound Blaster on a Retro Gaming PC: Period-Correct Audio and the Modern G6 Bridge
- Ollama vs vLLM for Single-User Local Chat on an RTX 3060 12GB (2026)
- Best 4K Gaming Monitor for the PS5 Pro and PC in 2026
More buying guides from SpecPicks
Browse all buying guides →- Best CPUs for Content Creators in 2026
- Best Graphics Cards for Gaming in 2026
- Best GPUs for Running Local LLMs in 2026
- Best CPUs for Gaming in 2026
- Best 4K Monitors for Content Creators in 2026
- Best Controllers for PC Gaming in 2026
- Best AM5 Motherboards for 2026
- Best Gaming Monitors for 2026
- Best Gaming Mice for 2026
- Best NVMe SSDs for Gaming in 2026
- Best Tools for Building and Repairing Retro PCs in 2026
- Best CPU Coolers for 2026
- Best NVMe External Enclosures for 2026
- Best GPUs for 4K Gaming in 2026
- Best 1440p 240Hz Gaming Monitors in 2026
- Best External SSDs for Content Creators in 2026
- Best Retro Gaming Consoles & Handhelds for 2026
- Best DDR5 RAM for Gaming PCs in 2026
- Best GPU for Running 27B-32B Local LLMs in 2026
- Best Mechanical Keyboards for Gaming in 2026
- Best PC Cases for Building in 2026