AI memory per dollar: Mac Studio, Strix Halo and Nvidia compared
Local AI shopping reduces to two numbers — how much memory a model can use, and how fast that memory moves. Here is every machine that plays, from a $3,449 Strix Halo box to a $16,000 Nvidia card, priced per gigabyte and per unit of bandwidth.
Strix Halo is the cheapest local AI memory in this comparison at $27 per gigabyte. Used Mac Ultras cost $34-$41 per gigabyte but provide roughly three times the memory bandwidth. Nvidia’s 32GB and 96GB cards lead on bandwidth and cost $147-$167 per gigabyte.
A machine for running models locally is mostly a memory purchase: the model must fit in memory the processor can address, and token speed is bounded by how fast that memory moves. Price every machine on those two axes and the market sorts into three groups that overlap much less than their stickers suggest.
Local AI memory prices compared
| Machine | Memory | Bandwidth | Price | $/GB |
|---|---|---|---|---|
| Framework Desktop (Strix Halo) | 128GB | 256GB/s | $3,449 new | $27 |
| Nvidia DGX Spark | 128GB | 273GB/s | $4,699 new | $37 |
| Mac Studio M1 Ultra, used | 128GB | 800GB/s | $5,249 | $41 |
| Mac Studio M3 Ultra, used | 512GB | 819GB/s | $17,448 | $34 |
| Mac Studio M3 Ultra, used | 256GB | 819GB/s | $9,999 | $39 |
| Mac Studio M5 Ultra | 96GB | 1.2TB/s | $5,499 new | $57 |
| Mac Studio M5 Max | 36GB | 614GB/s | $2,499 new | $69 |
| RTX 5090 | 32GB | 1.79TB/s | ~$4,700 street | $147 |
| RTX Pro 6000 | 96GB | 1.79TB/s | $16,000 | $167 |
Which machine has the cheapest local AI memory?
If the question is purely “how many gigabytes can I point a model at per dollar,” the Strix Halo machines win: AMD’s Ryzen AI Max+ 395 with 128GB of unified LPDDR5X, sold as the Framework Desktop and several mini-PCs, at $27 a gigabyte. It is also x86 Linux, repairable and ugly in the way a person who distrusts aluminum jewel boxes might prefer.
The catch is the second axis. That memory moves at 256GB/s — a third of a used M1 Ultra’s bandwidth, a fifth of the M5 Ultra’s — and token generation is bandwidth-bound. Community benchmarks put 70B models at single-digit tokens per second on both Strix Halo and Nvidia’s DGX Spark. The models fit; they don’t hurry. The DGX Spark makes the same trade at a worse price, and sells CUDA and Nvidia’s stack for the difference.
Which machine offers the most memory bandwidth for the price?
Among machines that hold serious models, the Macs own the bandwidth column: 800GB/s on Ultras Apple sold in 2022, 1.2TB/s on the new M5 Ultra. Nvidia’s cards move memory faster still — but at $147 to $167 per gigabyte, capacity is what you give up. A 32GB RTX 5090 cannot hold a 4-bit 70B model at all, and the 96GB card that can costs $16,000 after its August repricing, more than two used 96GB M3 Ultras ask.
Which is why the used Ultras are the quiet value rows. A used M1 Ultra with 128GB — the same memory count as the Strix Halo box, at three times its bandwidth — ran a $5,249 median ask in our Aug. 18-25 observations. The used 256GB and 512GB M3 Ultras price memory at $34-39 a gigabyte with 819GB/s behind it: no other path to a half-terabyte of model-addressable memory in one box comes close. Their absolute prices are high because the shortage repriced them; their per-gigabyte prices are mid-table anyway.
Above 512GB, the question changes from choosing one machine to pricing a Mac Studio cluster.
Why local AI hardware got more expensive in 2026
The comparison is a snapshot of a market that has repriced violently in one direction. The Framework Desktop’s 128GB configuration sold for $1,999 in mid-2026 and was out of stock at $3,449 in early August. Nvidia raised the DGX Spark from $3,999 to $4,699 citing the LPDDR5X shortage, and took the RTX Pro 6000 from $8,565 at launch to $16,000 in about ten months. Against that, Apple’s June repricing — 14-33% across the Mac line — was, strange to write, the restrained one. Memory is what all of these machines are made of, and memory is what the AI buildout is consuming; nobody sells an exit from that.
For what these memory sizes actually run, model by model, see the fit table. And if the numbers here age — they will — the data note carries the dates.
About the data: New-unit prices are manufacturer or median street prices as reported in August 2026, linked in place; PC prices for identical hardware currently spread widely between vendors and change fast. Used Mac Studio figures are median asking prices from our crawler, Aug. 18-25, secondhand conditions, one price per listing, scam-shaped listings excluded; asking prices are not completed sales. Bandwidth figures are manufacturer specifications. Tokens-per-second claims are community-reported, labeled where used.