Datasheet for local AI49 models98 GPUsData read 2026-09-25
No adsNo tracking
Check my GPU →

Mac 128 GB vs Radeon 8060S (Strix Halo) 96 GB for local AI

The Mac 128 GB has 19.4 GB more memory, and that decides it for local AI: it runs a better file (or runs at all) for 0 of 49 models, and 49 run at 8-bit or better against 49. Memory is only half the story here: the Mac holds more, but it is several times slower per image than a desktop RTX card, and FP8 files do not work on it.

Mac 128 GB
VRAM
115.4 GB
Memory
Unified
Bandwidth
—
Architecture
Apple Silicon
FP8 compute
No
Power
—

All models on it →

VS
Radeon 8060S (Strix Halo) 96 GB
VRAM
96 GB
Memory
LPDDR5X (shared system memory)
Bandwidth
256 GB/s
Architecture
RDNA 3.5
FP8 compute
No
Power
—

All models on it →

01Model by model

ModelMac 128 GBRadeon 8060S (Strix Halo) 96 GB
image models
FLUX.1 devRuns well 16-bitRuns well 16-bit
FLUX.1 schnellRuns well 16-bitRuns well 16-bit
FLUX.1 KontextRuns well 16-bitRuns well 16-bit
FLUX.1 KreaRuns well 16-bitRuns well 16-bit
FLUX.1 FillRuns well 16-bitRuns well 16-bit
FLUX.2 devRuns well 16-bitRuns well 16-bit
FLUX.2 klein 9BRuns well 16-bitRuns well 16-bit
FLUX.2 klein 4BRuns well 16-bitRuns well 16-bit
Krea 2Runs well 16-bitRuns well 16-bit
Qwen-ImageRuns well 16-bitRuns well 16-bit
Qwen-Image-EditRuns well 16-bitRuns well 16-bit
Qwen-Image 2.1Runs well 16-bitRuns well 16-bit
Z-Image TurboRuns well 16-bitRuns well 16-bit
Z-ImageRuns well 16-bitRuns well 16-bit
Ideogram 4Runs well Q8_0Runs well Q8_0
Boogu-ImageRuns well 16-bitRuns well 16-bit
ERNIE-ImageRuns well 16-bitRuns well 16-bit
HiDream-O1Runs well 16-bitRuns well 16-bit
Mage-FlowRuns well 16-bitRuns well 16-bit
Lumina 2.0Runs well 16-bitRuns well 16-bit
HiDream-I1 FullRuns well 16-bitRuns well 16-bit
HiDream-I1Runs well 16-bitRuns well 16-bit
SD 3.5 LargeRuns well 16-bitRuns well 16-bit
SD 3.5 MediumRuns well 16-bitRuns well 16-bit
Chroma1-HDRuns well 16-bitRuns well 16-bit
SDXLRuns well 16-bitRuns well 16-bit
Illustrious / PonyRuns well 16-bitRuns well 16-bit
SD 1.5Runs well 16-bitRuns well 16-bit
HunyuanImage 2.1Runs well 16-bitRuns well 16-bit
video models
Wan 2.1 14BRuns well 16-bitRuns well 16-bit
Wan 2.1 1.3BRuns well 16-bitRuns well 16-bit
Wan 2.1 I2V 480PRuns well 16-bitRuns well 16-bit
Wan 2.1 I2V 720PRuns well 16-bitRuns well 16-bit
Wan VACE 14BRuns well 16-bitRuns well 16-bit
Wan 2.2 T2VRuns well 16-bitRuns well 16-bit
Wan 2.2 I2VRuns well 16-bitRuns well 16-bit
Wan 2.2 5BRuns well 16-bitRuns well 16-bit
Wan 2.2 AnimateRuns well 16-bitRuns well 16-bit
Wan Animate 2Runs well 16-bitRuns well 16-bit
Wan 2.2 S2VRuns well 16-bitRuns well 16-bit
SCAIL-2Runs well 16-bitRuns well 16-bit
HunyuanVideo 13BRuns well 16-bitRuns well 16-bit
LTX-Video 13BRuns well 16-bitRuns well 16-bit
HunyuanVideo 1.5Runs well 16-bitRuns well 16-bit
LTX-2Runs well 16-bitRuns well 16-bit
LTX-2.3Runs well 16-bitRuns well 16-bit
LTX-2.5Runs well 16-bitRuns well 16-bit
MiniMax H3Runs well 16-bitRuns well 16-bit
MiniMax H3 PrunedRuns well 16-bitRuns well 16-bit

Highlighted: the GPU that runs a better file for that model. Launch prices are the maker’s original list prices, not today’s street prices. Calculated from real file sizes; how the numbers work.

02Score

49run well on Mac 128 GB
49run well on Radeon 8060S (Strix Halo) 96 GB
0better on Mac 128 GB
0better on Radeon 8060S (Strix Halo) 96 GB