AI Master · 17:35 · 21 Jul 2026 watched + fact-flagged

“Apple Just Killed AI Subscriptions Forever”
— what’s actually in it

A buy/wait/skip review of the Mac Mini M4 Pro (48 GB) as an always-on local-inference box. The headline is clickbait; the spec correction and the Bloomberg roadmap are the parts worth keeping.

The one correction the whole video hangs on

550 GB/s  →  273 GB/s

Every benchmark citing 546–550 GB/s for a Mac Mini is quoting the M4 Max. The Mac Mini ships the M4 Pro — exactly half the memory bandwidth. If a reviewer quotes 550 on a Mini, they have the wrong chip or the wrong box.

Model fit on 48 GB @ 273 GB/s video’s claimed numbers

Model classDecodeFeel
Qwen3-30B-A3B (MoE)40–75 tok/sfastest thing on the boxgreat
GPT-OSS-20B~34 tok/sgenuinely fastgreat
7–8B dense20–30 tok/sresponsivegreat
14B dense10–20 tok/scomfortablefine
30–32B dense12–18 tok/sreads as inference, not chatworkable
70B dense3–5 tok/syou feel every responsewall
GPT-OSS-120Bneeds ≥60 GB; won’t loadno fit

Escape hatches he names: 70B → M4 Max /128 GB at 12–13 tok/s. 120B-class → the AMD Strix Halo box, which he measured at 34 tok/s on GPT-OSS-120B. He concedes that round to AMD outright.

Cost of memory $ per GB of unified RAM

Box$/GBRead
GMKtec Evo X2 (Strix Halo, 128 GB)$12capacity king
Framework Desktop$18
DGX Spark$37
Mac Mini M4 Pro (48 GB)$42≈$2,399 as configured
Mac Studio M3 Ultra$55worst $/GB on the board

Apple loses on pure memory value and he says so. Where it wins is watts: 30–65 W under real inference load vs 45–140 W for Strix Halo and 700–800 W for an RTX tower. That’s the entire case for the Mini — a 24/7 agent loop that costs nothing to leave running.

The June 25 price move

Roadmap Mark Gurman / Bloomberg — rumor, not shipped

Oct–Nov 2026
M5 Mac MiniRumored, unconfirmed. M5 Max already ships in MacBook Pro: 128 GB, 614 GB/s. Ollama 0.19 (Mar 2026) added an MLX backend that roughly doubled decode on M5 Max.
Late 2026
Base M6 only — ~200 GB/sThe headline: M6 Pro, M6 Max and M6 Ultra are being skipped entirely. First time in the Apple Silicon era. There is no high-bandwidth M6 Mini coming.
H1 2027
M7 — fast-trackedInternal framing is reportedly “approaching Nvidia Blackwell.”
2028
M7 Ultra — 1.5 TB unified memoryPlus: M5 Ultra has reportedly been tested internally at 768 GB.

The bear case the useful half of the video

His verdict

Buy now

You need a 24/7 always-on inference box today.

  • 7B–32B, or 30B-class MoE
  • Agentic workflows / private inference
  • Ollama + LM Studio just work
  • Go in knowing it’s 273 GB/s

Wait ~90 days

You’re not in a rush and you care about throughput.

  • M5 Mini rumored this fall
  • MLX-backend gains on M5 Max are real
  • Perf-per-dollar likely shifts

Before you act on any of it