Mac mini, M5 Pro vs DGX Spark, 64 GB (partners only)
Specs checked 2026-10-15; prices re-checked 2026-10-20. Derived numbers are bounds, not measurements (rules). We make a Mac app (Akhna); read the Mac column with that in mind.
Specs
| Mac mini, M5 Pro | DGX Spark, 64 GB (partners only) | |
|---|---|---|
| Memory | 24, 48 or 64 GB spec [S5] | 64 GB spec [S18] |
| Usable for the model, per option derived | 24 GB → 18.0 GB usable, ~32B at 4-bit 48 GB → 36.0 GB usable, ~64B at 4-bit 64 GB → 48.0 GB usable, ~85B at 4-bit | 64 GB → 48.0 GB usable, ~85B at 4-bit |
| Bandwidth | 307 GB/s spec [S5] | 273 GB/s cited [S17] |
| Published compute | not published spec [S5] | same chip as the 128 GB unit spec [S18] |
| Power | 155 W max continuous spec [S5] (whole computer) | as the 128 GB unit spec [S15] (whole computer) |
| Software | Metal, MLX; no CUDA | CUDA on Arm (aarch64 packages) |
| Prices | $1,699: 24 GB / 512 GB (2026-08-25) cited [S13] $2,699: 64 GB / 512 GB ($1,699 + $1,000) (2026-08-25) derived [S13] | $4,999: partner units, from (2026-10-02) spec [S18] [S17] |
Bandwidth ratio: 1.12x derived. For one user writing an answer, the decode ceiling scales with it (rule 1), as long as the model fits both.
Answer speed ceilings, tokens/s derived
| Model (4-bit) | Mac mini, M5 Pro | DGX Spark, 64 GB (partners only) |
|---|---|---|
| 8B dense (Llama 3 8B shape), short context | 68 | 61 |
| 8B dense (Llama 3 8B shape), 32,768 tokens | 35 | 31 |
| 30B-A3B MoE (Qwen3-30B-A3B), short context | 165 | 147 |
| 30B-A3B MoE (Qwen3-30B-A3B), 32,768 tokens | 60 (48 / 64 GB only) | 54 |
| 70B dense (Llama 3 70B shape), short context | 8 (64 GB only) | 7 |
| 70B dense (Llama 3 70B shape), 32,768 tokens | does not fit | does not fit |
| 235B-A22B MoE (Qwen3-235B-A22B), short context | does not fit | does not fit |
Time to read a 16,000-token prompt derived
Neither maker publishes a dense FP16/BF16 peak, so no floor can be derived: prefill on these two has to be measured.
Where to look
Apple Mac mini · NVIDIA DGX Spark (maker pages)
Sources
- [S1] Apple, Mac Studio tech specs
- [S2] Apple newsroom, new Mac Studio with M5 Max and M5 Ultra (2026-08-25)
- [S3] Apple, Mac Studio buy page
- [S4] Apple, MacBook Pro tech specs
- [S5] Apple, Mac mini tech specs
- [S7] Apple Support, Mac Studio power consumption and thermal output
- [S9] Daring Fireball, M5 Max Mac Studio base prices (2026-08-25)
- [S10] EveryMac, Mac Studio M5 Max 18-core CPU / 40-core GPU
- [S12] MacRumors, 512 GB M5 Ultra in October (2026-08-25)
- [S13] Macworld, M6 and M5 Pro Mac mini prices (2026-08-25)
- [S14] NVIDIA, DGX Spark product page
- [S15] NVIDIA docs, DGX Spark hardware overview
- [S16] The Register, GB10 workstations arrive (2025-10-13)
- [S17] The Register, $4,999 64 GB DGX Spark; 128 GB to $6,950 (2026-10-02)
- [S18] NVIDIA blog, DGX Spark 64 GB (2026-10-02)
- [S19] StorageReview, DGX Spark review (2025-10-14)
- [S21] Tom's Hardware, DGX Spark $3,999 to $4,699 (Feb 2026; headline read)
- [S22] AMD, Ryzen AI Max+ 395 specifications
- [S23] AMD blog, Variable Graphics Memory FAQ (2025-07-29)
- [S24] AMD, Ryzen AI Halo with Ryzen AI Max+ PRO 495
- [S25] AMD blog, Ryzen AI Halo and Ryzen AI Max PRO 400 series (2026-05-20)
- [S26] AMD ROCm on Radeon and Ryzen, Linux support matrices (7.2.1)
- [S27] Framework, Desktop DIY Edition (prices, stock)
- [S28] Framework, Desktop overview
- [S29] Framework blog, 192 GB Framework Desktop pre-order (2026-09-30)
- [S31] Tom's Hardware, $3,999 Ryzen AI Halo (headline read)
- [S32] NVIDIA, RTX Blackwell GPU architecture whitepaper (Table 3)
- [S33] NVIDIA, GeForce RTX 5090 product page
- [S34] NVIDIA, GeForce RTX 4090 product page
- [S35] NVIDIA, GeForce compare page
- [S36] NVIDIA newsroom, RTX 50 series prices (2025-01-06)
- [S37] GPU Poet, RTX 5090 prices September 2026 (eBay listings)
- [S38] Wikipedia, GeForce RTX 40 series
- [S39] NVIDIA, RTX PRO 4000 Blackwell
- [S40] NVIDIA, RTX PRO 6000 Blackwell
- [S42] Llama 3 paper, Table 3
- [S43] Qwen3-30B-A3B model card
- [S44] Qwen3-30B-A3B config.json
- [S45] Qwen3-235B-A22B model card
- [S46] MLX docs, mlx.core.quantize
- [S47] mlx-lm README
- [S48] Rajbhandari et al., ZeRO
- [S49] Let's Data Science, RTX PRO 6000 price (2026-08-12)
- [S50] PCMag via Yahoo, $3,999 DGX Spark (2025-10-13)
- [S51] NVIDIA Developer Forums, 2/23/2026 price change (search result)
- [S52] Phoronix, Framework Desktop PRO 495 from $6,799 (2026-09-30)
- [S53] Let's Data Science, Strix Halo mini PC for $3,999 (2026-07-06)
- [S54] gpuprix, RTX PRO 4000 Blackwell US prices
- [S55] SHI, PNY RTX PRO 4000 Blackwell (search result)
- [S56] Intel, Thunderbolt 5 technology brief
- [S57] EveryMac, Mac Studio M5 Ultra 30-core CPU / 64-core GPU
- [S58] Daring Fireball, configurations and pricing for new Mac minis and Mac Studios (2026-08)
- [S59] Framework, Desktop DIY (Max+ PRO 495) configurator: SSD extra or bring your own; Batch 2 ships November (read 2026-10-20)
- [S60] Borncity, Ryzen AI Halo 192 GB at Micro Center for $7,299 (2026-10-14)
- [S61] PCWorld, the RTX Spark laptops available at launch (2026-10-08)
- [S20] NVIDIA docs, RTX Spark porting guide, system overview
- [S62] Apple, Mac Studio configurator (36/80-core M5 Ultra, 512 GB, 16 TB: $29,799; option steps shown; ships 10-12 weeks; read 2026-10-30)
Accessed 2026-10-15; volatile prices re-checked 2026-10-20.