Mac Studio M5 Ultra (base config) for local AI in the UK
Not ranked yet: fewer than 3 reference-model tests in every size class (low sample).
Key facts
- Cheapest UK price
- £5,499 new
- Memory
- 96 GB
- Memory bandwidth
- 1200 GB/s
- Largest model it can run
- ~156B parameters at 4-bit (estimate: ~0.6 GB per billion parameters + ~2 GB overhead)
- Shop
- eBay UK (used)
- £5,499 new: Apple UK Store 'From' price, base config, checked 2026-10-20 (source)
Disclosure: eBay "Shop" links are affiliate links (marked rel="sponsored"): if you buy, we may earn a small commission at no extra cost to you. Rankings are never affected by commission.
Speed and value by model size
| Size class | Fits at 4-bit? | Speed | £ per tok/s | Value rank | Reference model |
|---|---|---|---|---|---|
| 7-9B models | Yes | 179.1 words/sec* only 1 test ⚠ | £31 | low sample (n=1) ⚠, not ranked | Llama 2 7B Q4_0 |
| 12-14B models | Yes | no verified data yet | – | not ranked | Gemma 4 12B Q4_0 |
| 27-35B models | Yes | no verified data yet | – | not ranked | Qwen 3.6 27B Q4_K_M |
| 70B+ models | Yes | no verified data yet | – | not ranked | no reference model yet |
Speed is the median single-user decode speed running the like-for-like reference model for that class, in tokens per second (*a token is roughly ¾ of a word, so words/sec is a rough guide). Ranks use the cheapest UK price and need at least 3 test runs; ⚠ = low sample, shown but not ranked. "Fits" means the model fits fully in memory at ~4-bit. How we measure.
Other models measured
- Llama 2 7B F16 (7.0B, 7-9B class): 73.6 tok/s only 1 test ⚠ · run
- Llama 2 7B Q8_0 (7.0B, 7-9B class): 119.0 tok/s only 1 test ⚠ · run
Shown for information only: these don't affect rank. Mixture-of-experts models (names with "a3b", "moe" and similar) run much faster than their size suggests.
Similar price alternatives
- RTX 4090 24GB £2,200 used · 24 GB · 167.7 tok/s on 7-9B · #19 of 23 for 7-9B
- AMD Strix Halo (Ryzen AI Max+ 395) 128GB £2,830 new · 128 GB · 50.6 tok/s on 7-9B · #23 of 23 for 7-9B
- Mac Studio M5 Max 40-core GPU (base config) £3,099 new · 48 GB · 111.6 tok/s on 7-9B · #22 of 23 for 7-9B
- RTX 5090 32GB £4,240 used · 32 GB · 292.5 tok/s on 7-9B · #20 of 23 for 7-9B
See the Mac Studio M5 Ultra (base config) on the leaderboard → · All cards · Beginner's guide · Methodology
Weekly UK value moves, by email
Price drops, new benchmark results, best buys under £500 / £1,000 / £2,000.
Check your inbox to confirm: we use double opt-in, so you're only added after clicking the link in the confirmation email. Free; unsubscribe any time. Sent via Mailchimp (see their privacy notice).