Apple refreshed the lineup on 25 August 2026: the Mac mini M6 (from $899, 153–170 GB/s), the Mac mini M5 Pro (from $1,699, 307 GB/s), and a new Mac Studio with M5 Max (from $2,499, up to 614 GB/s) and M5 Ultra (from $5,499, 1.2 TB/s, up to 512 GB unified memory). Preorder now, ships 22 September. RAM is still the deciding factor — buy the most you can.
The picks below include the new machines. Until they ship on 22 September, every speed figure for M6 and M5 Ultra is estimated from Apple’s published memory bandwidth via the LLMCheck model — no one has measured them yet, including us. The outgoing M4-generation Macs stay listed: they are discounted, still excellent, and every number for them is unchanged.
● Lineup: 25 August 2026 · Prices via Amazon
Already own a Mac? Check what it can run →
Four machines cover almost everyone. Every recommendation is benchmark-driven and never influenced by affiliate commissions.
Pick the largest model class you care about. We'll show the one Mac to buy — and one alternative.
🧠 Answer 3 questions — the Mac Advisor picks your config →
Already know your Mac? See the best LLMs for your exact Mac →
Sorted by price. Memory bandwidthd and max RAM are shaded by value — greener is more. See the full model leaderboard and benchmark data.
| Mac | Chip | Max RAM | Bandwidthd | GPU cores | Sample tok/s | Largest tier | From $ | |
|---|---|---|---|---|---|---|---|---|
| Mac mini M4 | M4 | 24GB | 120 GB/s | 10 | ~95 (Gemma 4 E2B) | ~14B dense | $599 | Check Price on Amazon → |
| MacBook Air M4 | M4 | 32GB | 120 GB/s | 10 | ~90 | ~14B dense | $1,099 | Check Price on Amazon → |
| Mac mini M4 Pro | M4 Pro | 64GB | 273 GB/s | 16–20 | ~32 (Qwen 3.6-35B-A3B, est.) | 32B MoE | $1,399 | Check Price on Amazon → |
| MacBook Pro M5 Pro | M5 Pro | 64GB | 273 GB/s | 16–20 | ~32 (Qwen 3.6-35B-A3B, est.) | 32B MoE | $1,999 | Check Price on Amazon → |
| Mac Studio M4 Max | M4 Max | 128GB | 546 GB/s | 32 | 70B sustained | 70B / GLM-4.5-Air | $1,999 | Check Price on Amazon → |
| MacBook Pro M5 Max | M5 Max | 128GB | 600 GB/s | 40 | ~52 (Qwen 3.6-35B-A3B, est.) | 70B / GLM-4.5-Air | $3,499 | Check Price on Amazon → |
| Mac Studio M4 Ultra | M4 Ultra | 192GB | 1,092 GB/s | 80 | ~30 (GLM-4.5-Air, est.) | 192GB / 405B Q2 | $3,999 | Check Price on Amazon → |
| Mac Pro M4 Ultra Same compute as Studio Ultra + PCIe — niche; most buyers want the Studio. |
M4 Ultra | 192GB | 1,092 GB/s | 80 | ~38 | 192GB | $6,999 | Check Price on Amazon → |
tok/s measured on representative models in LLMCheck testing. Configs reflect each chip's maximum RAM tier. Compare specific chips: M5 Max vs M4 Max · M5 Pro vs M5 Max.
RAM determines which models you can load at all. Find your tier, see exactly what runs, and what won't.
Runs: Gemma 4 E2B, Maple Preview 20B-A1B, Nanbeige4.2-3B, Apertus 1.5 8B at ~95 tok/s.
Can't run: no 32B+ models — too little memory.
Check Price on Amazon →Runs: dense models up to ~14B plus small MoE — Gemma 4 E4B, Qwen 3 30B-A3B, Bonsai 27B (1-bit)
Can't run: tight for full 32B MoE — possible but no headroom for context.
Check Price on Amazon →Runs: Qwen 3.6-27B, Muse Glimmer 30B, KAT-Coder-V2.5 at ~62 tok/s. The sweet spot for most buyers.
Can't run: no 70B models.
Check Price on Amazon →Runs: 32B-class with long context — Qwen 3.6-27B, Qwen3-Coder-Next with large context windows. ~56–62 tok/s.
Can't run: 70B is marginal — quantized only, slow.
Check Price on Amazon →Runs: 70B-class models, GLM-4.5-Air (~27 tok/s est.), and DeepSeek V4 Flash at 2-bit (~39 tok/s, community-reported on M5 Max). Comfortable for 24/7 agents.
Can't run: no 405B-class frontier models.
Check Price on Amazon →Runs: MiniMax M2.5 (~33 tok/s est.), Apertus 1.5 70B, and GLM-4.5-Air (~45 tok/s est.). For Inkling-Small and GLM 5.2 1-bit you want the M3 Ultra 256–512GB tier.
Caveat: frontier-class quants trade speed for capacity (~15–20 tok/s). Great for capacity, not raw speed at the very top end.
Check Price on Amazon →The frontier open models — GLM 5.2, Kimi K3, Qwen3.8-Max and DeepSeek V4 Pro — are server-class and won't run even on a 192 GB Mac Studio. To run the full, unquantized model, rent a datacenter GPU by the minute on Vast.ai — often 5–6× cheaper than AWS or GCP, with H100s and B200s available on demand.
Vast.ai referral link — we may earn a small commission at no extra cost to you. It never influences our reviews or rankings.
We'd rather you buy once and buy right. These are the things that actually change which Mac you should get.
Unified memory is soldered and can never be upgraded — buy the most RAM you can afford; it's the #1 factor in which models you can run.
Apple has no affiliate program. Amazon sells the identical Macs; we may earn a commission at no extra cost to you. It never influences our rankings.
Apple Certified Refurbished and Amazon Renewed offer the same machines for less — worth checking before you buy new, and often enough to afford the next RAM tier.
Memory bandwidth (GB/s), not just RAM size, drives tok/s — a Max chip is far faster than a Pro at the same RAM.
Local models are 4–250GB each. External storage and fast I/O keep your model library out of your boot drive.
Models are 4–250GB each — a 4TB portable SSD holds a serious library without filling your Mac's internal drive.
Check Price on Amazon →Pair an NVMe drive with a Thunderbolt 5 enclosure for a fast external model library that loads weights quickly.
Check Price on Amazon →For a desktop Mac mini or Studio — add displays, storage, and Ethernet over a single Thunderbolt 5 connection.
Check Price on Amazon →As an Amazon Associate, LLMCheck earns from qualifying purchases. The links above are affiliate links — they cost you nothing extra and help keep our benchmarks free and ad-light. Affiliate relationships never influence our rankings or recommendations; see our methodology for exactly how we score Macs and models.