Unverified50% confidenceFactExact time
Mac users should note: rapid-mlx reports that the M3 Ultra measured a peak of 72.7 GB at 1K context, while also stating that 96 GB Macs have not been verified and that image input and MTP are not enabled; to use vision capabilities on a Mac, you need to go through llama.cpp with an mmproj file.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedOn 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 3.07.79% similarUnverifiedThe blogger ran Gemma 3 12B with no difficulty on a Mac Mini with 16 GB of RAM and an M2 Pro chip.76% similarUnverifiedRunning LFM2.5-24B-A2B on macOS + Apple Silicon via MLX (mlx-lm>=0.32.0) can achieve over 150 tokens/second within 16GB of memory.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1049457API
curl https://kongchang.com/api/v1/knowledge/claims/1049457MCP
get_claim(id=1049457)