Local AI speed on Mac and DGX Spark racks
Mac Studio M5 Ultra
Generation speed in tokens per second, one request at a time, 4-bit builds.
| Tier | Best model | 4-bit size | Smallest Mac that fits | Price |
|---|---|---|---|---|
| Loading data… | ||||
Top model of each tier, on every rack
Tokens per second for each tier's best local model on a rack of M5 Ultras (512 GB or 256 GB Macs, as many as the model needs) and on four single machines, with Claude Sonnet 5.5's cloud API speed on top for scale.
The racks
Generation speed is mostly limited by memory bandwidth; memory size decides what fits.
| Rack | Chip | GPU cores | Bandwidth | Max memory | Price (US) |
|---|
Measured and estimated
Measured numbers are single-request generation speeds from public reviews and benchmark reports, without speculative decoding. Each one links to its source. Engines and quants differ between reports, so treat differences under about 15% as noise.
Estimates (striped bars, “≈ … est.”) fill cells where no run was found, and always start from a measured number. For the M1 Ultra, a measured M5 Ultra speed is scaled by the two chips' speeds in llama.cpp's Apple Silicon benchmark (83.73 vs 179.10 tokens/sec). For Nanbeige4.3-33B, a dense model, Qwen3.8 27B's measured speed on the same rack is scaled by file size. GLM-5.3 on one M5 Ultra is LLMCheck's estimate.
Racks of several M5 Ultras split the model across Macs over Thunderbolt 5 with RDMA (tensor parallelism in MLX). The anchor is Apple's measurement of Muse Spark Open (816B total, 42B active, 493 GB at 4-bit): 24.99 tokens/sec on 2 Macs and 36.73 on 4. GLM-5.3 has a similar shape, so 2× 256 GB is estimated at the same 25. Kimi K3.1 Pro on 4× 512 GB is the 4-Mac figure scaled by active parameters (42B / 104B). Kimi needs 7 Macs with 256 GB; no run that large is published.
Prices are US prices for the configuration shown (most memory, base storage), taken from Apple, NVIDIA or retailer listings in November 2026; a rack's price is the number of Macs times the price of one. The MacBook Pro price is approximate and the M1 Ultra, now discontinued, shows its 2022 launch price. Hover a price for its configuration and click it for the source.
Doesn't fit means the 4-bit build is larger than the rack's maximum memory. Sonnet 5.5 is the median API output speed from Artificial Analysis; it runs on Anthropic's servers, not a rack.
Data files: rack-speed-2026-11-18.csv, racks-2026-11-18.csv.