Unverified50% confidenceBenchmarkExact time
On a Mac Studio (Apple M3 Ultra, 96 GB memory), in tests using mflux 0.19.1, 8-bit quantized weights, and 1600x896 resolution, ERNIE-Image Turbo averaged a score of 4.28 (out of 5) while FLUX.2 klein 4B averaged 3.07.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedThe M5 Ultra Mac Studio running Cyberpunk 2077 at ultra settings with AI super-sampling disabled achieves 178 fps at 1080P, 131 fps at 2K, and maintains 68.8 fps at 4K.73% similarUnverified27B稠密模型在24GB M4 Pro Mac mini上使用4-bit量化可以运行，速度约为11 tok/s72% similarUnverifiedIQ4_XS量化文件大小15.57GB，pp2048为95.4 tok/s，tg128为10.9 tok/s71% similarVerifiedAfter 4-bit quantization, Llama 3.3 70B has a model size of approximately 40 GB and can run on a Mac Studio with 64 GB of memory or a single professional GPU with 48 GB of VRAM.70% similarUnverifiedApple claims the M5 Ultra's peak AI computing performance is 4.3 times that of the M3 Ultra, with memory bandwidth 50% higher than the M3 Ultra.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1048848API
curl https://kongchang.com/api/v1/knowledge/claims/1048848MCP
get_claim(id=1048848)