Different platforms, same budget
NVIDIA DGX Spark vs Apple Mac Studio · M5 Ultra
Memory, bandwidth, software stack, price and the models each one can hold. Generated from the two sourced machine records; estimates are labelled.
NVIDIA GB10
NVIDIA DGX Spark
128 GB unified
Open the record
Apple Silicon
Apple Mac Studio · M5 Ultra
96 GB unified · selected model
Open the recordWhat actually differs
- Different software stacks: the NVIDIA DGX Spark runs CUDA, the Apple Mac Studio · M5 Ultra runs MLX and Metal. Check that your runtime and model format are supported before comparing numbers.
- The NVIDIA DGX Spark has 32 GB more model memory (128 GB vs 96 GB). That decides which models fit at all.
- Memory bandwidth is not in the record for the Apple Mac Studio · M5 Ultra, so the Lab cannot compare generation speed ceilings.
- No public list price in the record for the Apple Mac Studio · M5 Ultra. Ask the supplier for a configured quote.
- Form factor: Desktop AI system vs Mini workstation.
Which models fit
Estimate · 4-bit · 8K context · 1 request| Model | NVIDIA DGX Spark | Apple Mac Studio · M5 Ultra |
|---|---|---|
| Llama 3.1 8B | Fits 16 GB≤ 48 tok/s | Fits 16 GBBandwidth not in record |
| Qwen3 14B | Fits 20 GB≤ 28 tok/s | Fits 20 GBBandwidth not in record |
| Qwen3 32B | Fits 32 GB≤ 13 tok/s | Fits 32 GBBandwidth not in record |
| Llama 3.3 70B | Fits 54 GB≤ 6.3 tok/s | Fits 54 GBBandwidth not in record |
| gpt-oss-20b (MoE) | Fits 23 GB≤ 110 tok/s | Fits 23 GBBandwidth not in record |
| gpt-oss-120b (MoE) | Fits 80 GB≤ 77 tok/s | Fits 80 GBBandwidth not in record |
| Qwen3 235B-A22B (MoE) | Too large 151 GB | Too large 151 GB |
| DeepSeek V3 / R1 671B (MoE, MLA) | Too large 408 GB | Too large 408 GB |
Specifications
Sourced and dated| NVIDIA DGX Spark | Apple Mac Studio · M5 Ultra | |
|---|---|---|
| Chip / accelerator | GB10 Grace Blackwell Superchip | Apple M5 Ultra · 30-core CPU / 64-core GPU |
| Platform | NVIDIA GB10 | Apple Silicon |
| Model memory | 128 GB unified | 96 GB unified · selected model |
| Memory bandwidth | 273 GB/s | Not verified for selected M5 Ultra |
| Software stack | CUDA | MLX and Metal |
| Operating system | NVIDIA DGX OS | macOS |
| Storage | 4 TB NVMe | 1 TB · reference |
| Networking | 10 GbE · ConnectX-7 · Wi-Fi 7 | Confirm current M5 configuration |
| Form factor | Desktop AI system | Mini workstation |
| Dimensions | 150 × 150 × 50.5 mm | Confirm current M5 chassis specifications |
| Weight | 1.2 kg | Not verified |
| Power rating (not consumption) | 240 W adapter · 140 W SoC TDP | 480 W maximum continuous power rating · not typical consumption |
| Supplier list price | ≈ $4.7k · Supplier list price · United States · Sept 2026 | Preorder · price from the manufacturer · No public list price · manufacturer page |
| Availability | Listed for order · recheck with supplier | Apple lists availability from 22 September 2026 |
| Model configurations in the Lab | 6 | 3 |
| Setups in the Lab | 5 | 1 |
| Record reviewed | 2026-09-13 | 2026-09-13 |
Before you choose
NVIDIA DGX Spark
- Memory capacity does not establish interactive speed or simultaneous request capacity.
- UT has documented a Spark deployment. Confirm exact software versions and support scope.
Apple Mac Studio · M5 Ultra
- Apple store lists this configuration for pre-order, available from 22 September. No usable price was exposed in the reviewed store page.
- This is a new configuration. Runtime compatibility, actual GPU memory allowance and performance have not been validated by this lab.
NVIDIA DGX Spark compared with
ASUS Ascent GX10 Dell Pro Max with GB10 HP ZGX Nano G1n Lenovo ThinkStation PGX Acer Veriton GN100 GIGABYTE AI TOP ATOM MSI EdgeXpert Apple Mac Studio · M3 Ultra Framework Desktop · Ryzen AI Max+ MINISFORUM MS-S1 MAX HP Z2 Mini G1a AMD Ryzen AI Halo NVIDIA DGX StationApple Mac Studio · M5 Ultra compared with
Framework Desktop · Ryzen AI Max+ Apple Mac Studio · M3 UltraOwn one of these? A measured run (model revision, runtime, context, tokens per second) is worth more than this whole page. Publish it.