Same chip, different box
NVIDIA DGX Spark vs GIGABYTE AI TOP ATOM
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
NVIDIA GB10
GIGABYTE AI TOP ATOM
128 GB unified
Open the recordWhat actually differs
- Same GB10 platform. Model recipes carry over; the real differences are chassis, storage, cooling, support and price.
- Both have 128 GB unified, so the same models fit.
- Same memory bandwidth (273 GB/s), so the same decode ceiling for a model that fits on both.
- No public list price in the record for the GIGABYTE AI TOP ATOM. Ask the supplier for a configured quote.
Which models fit
Estimate · 4-bit · 8K context · 1 request| Model | NVIDIA DGX Spark | GIGABYTE AI TOP ATOM |
|---|---|---|
| Llama 3.1 8B | Fits 16 GB≤ 48 tok/s | Fits 16 GB≤ 48 tok/s |
| Qwen3 14B | Fits 20 GB≤ 28 tok/s | Fits 20 GB≤ 28 tok/s |
| Qwen3 32B | Fits 32 GB≤ 13 tok/s | Fits 32 GB≤ 13 tok/s |
| Llama 3.3 70B | Fits 54 GB≤ 6.3 tok/s | Fits 54 GB≤ 6.3 tok/s |
| gpt-oss-20b (MoE) | Fits 23 GB≤ 110 tok/s | Fits 23 GB≤ 110 tok/s |
| gpt-oss-120b (MoE) | Fits 80 GB≤ 77 tok/s | Fits 80 GB≤ 77 tok/s |
| 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 | GIGABYTE AI TOP ATOM | |
|---|---|---|
| Chip / accelerator | GB10 Grace Blackwell Superchip | GB10 Grace Blackwell Superchip |
| Platform | NVIDIA GB10 | NVIDIA GB10 |
| Model memory | 128 GB unified | 128 GB unified |
| Memory bandwidth | 273 GB/s | 273 GB/s |
| Software stack | CUDA | CUDA |
| Operating system | NVIDIA DGX OS | NVIDIA DGX OS |
| Storage | 4 TB NVMe | 1 TB Gen4 / 4 TB Gen4 / 4 TB Gen5 |
| Networking | 10 GbE · ConnectX-7 · Wi-Fi 7 | 10 GbE · ConnectX-7 · Wi-Fi 7 |
| Form factor | Desktop AI system | Desktop AI system |
| Dimensions | 150 × 150 × 50.5 mm | 150 × 150 × 50.5 mm |
| Weight | 1.2 kg | 1.2 kg |
| Power rating (not consumption) | 240 W adapter · 140 W SoC TDP | 240 W adapter |
| Supplier list price | ≈ $4.7k · Supplier list price · United States · Sept 2026 | Price from the manufacturer · No public list price · manufacturer page |
| Availability | Listed for order · recheck with supplier | Check regional availability |
| Model configurations in the Lab | 6 | 6 |
| Setups in the Lab | 5 | 5 |
| Record reviewed | 2026-09-13 | 2026-09-07 |
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.
GIGABYTE AI TOP ATOM
- GIGABYTE publishes three ATAGB10 variants differing in storage (1 TB Gen4, 4 TB Gen4, 4 TB Gen5). Confirm which variant a regional seller offers; no usable public price was verified on the review date.
- The ATOM shares NVIDIA's GB10 platform. Platform guidance applies; no Lab measurement exists for this exact chassis.
- Memory capacity alone does not establish speed, runtime compatibility or production capacity.
NVIDIA DGX Spark compared with
ASUS Ascent GX10 Dell Pro Max with GB10 HP ZGX Nano G1n Lenovo ThinkStation PGX Acer Veriton GN100 MSI EdgeXpert Apple Mac Studio · M3 Ultra Apple Mac Studio · M5 Ultra Framework Desktop · Ryzen AI Max+ MINISFORUM MS-S1 MAX HP Z2 Mini G1a AMD Ryzen AI Halo NVIDIA DGX StationOwn one of these? A measured run (model revision, runtime, context, tokens per second) is worth more than this whole page. Publish it.