Our rental machine is the M3 Ultra 512 GB model. The hardware specifications and benchmarks below describe this machine. Apple’s new M5 Ultra is a separate generation; see the dated availability information below and the Apple announcement and current Apple specifications.
The rental machine and Apple’s new lineup
- Does Apple offer a Mac Studio with 512 GB of memory?
- As of September 10, 2026, Apple has announced a Mac Studio with M5 Ultra and up to 512 GB of unified memory. Pre-orders for the new Mac Studio opened August 25; general availability is scheduled for September 22, with the 512 GB configuration coming in late October. Announcement and pre-order availability do not mean the 512 GB configuration has shipped.
- Which Mac Studio does AI KIZAI rent?
- Our rental machine is a Mac Studio M3 Ultra with 512 GB of unified memory and a 4 TB SSD. We do not offer an M5 Ultra rental. The specifications and measured benchmarks on this page describe the M3 Ultra machine.
- Can I use 512 GB of unified memory without buying a Mac?
- Yes. AI KIZAI offers dedicated remote access to one M3 Ultra 512 GB Mac Studio for 3, 7, 14 or 30 days, from $299 for 3 days. You connect over Tailscale using SSH, VNC, or macOS Screen Sharing; nothing is shipped. Remote access depends on machine availability and connection readiness. The rental period is counted from payment processing.
Hardware specifications
Source: Apple — Mac Studio (2025) technical specifications · Original M3 Ultra announcement (512 GB option)
- Chip
- Apple M3 Ultra
- CPU
- 32 cores
- GPU
- 80 cores
- Neural Engine
- 32 cores
- Unified memory
- 512 GB
- Memory bandwidth
- 819 GB/s
- Storage
- 4 TB SSD
- Thunderbolt
- Thunderbolt 5 × 6 (4 rear + 2 front)
- USB-A
- USB 3 × 2 (up to 5 Gb/s)
- HDMI
- HDMI 2.1 × 1
- Ethernet
- 10 Gb Ethernet
- Wi-Fi
- Wi-Fi 6E (802.11ax)
- Bluetooth
- Bluetooth 5.3
What 512 GB actually runs
With 512 GB of unified memory at 819 GB/s, the weights of frontier open-weight models stay fully resident — no sharding across GPUs, no offloading to disk. Ollama, llama.cpp, and MLX work out of the box on macOS.
- GLM-5.2 (744B MoE)
- 4-bit quant (~390 GB) fits entirely in memory — MIT license, 1M context
- DeepSeek-V3 / R1 (671B MoE)
- 4-bit quant (~380 GB) fits with no offloading to disk
- Kimi K2.7 Code (1T MoE)
- Runs at 2-bit quantization (~325 GB) with room for context
- DeepSeek V4-Flash (284B MoE)
- 4-bit (~145 GB) — huge headroom for context or a second model
- Qwen 3.6 / 70B-class
- Several models resident at once — hot-swap without reloading
Throughput depends on the model and quantization. Rent it and run your own benchmark — that is exactly what the short plans are for.
Measured throughput — on this exact machine
We rented our own machine through the normal checkout and benchmarked it over Tailscale like any customer (July 2026, single-run snapshots, 300 generated tokens, temperature 0):
- DeepSeek R1-0528 (4-bit MLX, 351.7 GiB)
- Generation 20.3 tok/s · peak 380.7 GB RAM — no swap, no OOM
- Kimi K2.7 Code (2-bit GGUF, 316.2 GiB)
- Generation 24.6 tok/s on llama.cpp — a 1T-parameter MoE on one Mac
- gpt-oss-120B (MXFP4 MLX)
- Generation 79.2 tok/s — and 62.6 tok/s even at a 32K-token prompt
- Qwen3.6 35B-A3B (4-bit MLX)
- Generation 94.6 tok/s, prompt processing 2,892 tok/s — fully interactive
- Qwen3-Coder-Next (4-bit MLX)
- 77.2 tok/s + a 29/29 local Codex agent soak on the same machine
Prompt processing, load times, peak memory, power draw, the failures, and every caveat are in the full benchmark write-up. Speed measurements only — not a model-quality comparison.
The rental environment
- Connection
- Tailscale (WireGuard) — SSH / VNC / macOS Screen Sharing
- Machine type
- Dedicated bare metal — not shared, not virtualized
- Uptime
- Runs 24/7 for your whole rental period
- Your account
- Your own macOS administrator user
- Security
- No open inbound ports; end-to-end encrypted tunnel only
- Network
- 1 Gbps fiber, hosted in Kobe, Japan
- Start
- Subject to machine availability; access details follow checkout and machine assignment
Pricing — one-time payment, no subscription
- 3 days
- $299 (~$100/day)
- 7 days
- $499 (~$71/day)
- 14 days
- $799 (~$57/day)
- 30 days
- $1,499 (~$50/day)
Pay once with Stripe Checkout (cards, Apple Pay, Google Pay). Your rental ends when the purchased period is over — nothing renews, nothing to cancel.
What people rent it for
Frontier open-weight models
Run the current open-weight frontier (GLM-5.2, Kimi K2.7, DeepSeek R1 / V4-Flash) locally over Ollama, llama.cpp, or MLX — no API rate limits, no per-token billing.
AI agents, running 24/7
Keep Claude Code, Codex, or autonomous agents running around the clock on a machine that is not your laptop. Multiple models stay resident.
Try before you buy
Measure memory use and performance on our M3 Ultra 512 GB machine before deciding whether to buy hardware. Results describe this M3 Ultra, not the performance of a newer Mac.
Research & prototyping
Benchmark quantizations, test fine-tuned weights, or run evaluations on hardware you could not otherwise access — for exactly as long as you need.
Rent the 512 GB machine
3 days from $299. Access is subject to machine availability and assignment.
Weighing this against renting GPUs? See Mac Studio vs cloud GPU. 日本語版は ai-kizai.jp へ。