Ascent GX10
The volume workhorse — 1 TB base SKU, TAA-compliant variant for public sector, stackable chassis design.
Price
£4,299 inc VAT
1 TB SKU, Scan UK in stock · US $3,099.99 (1 TB)
verified 2026-07 · supply & lease options in every proposal
ASUS- 128 GB
- Unified memory
- 273 GB/s
- Memory bandwidth
- 1 PFLOP
- Sparse FP4 compute
- 240 W
- Wall power
one coherent CPU+GPU pool
the tok/s ceiling
1,000 AI TOPS
standard socket, near-silent
ASUS ships the GB10 platform as the Ascent GX10, leading with a 1 TB base configuration that launched at £2,999.99 — the February 2026 price rise hit this SKU hard, and it now lists at £4,299 at Scan.
A TAA-compliant SKU exists for public-sector procurement, and the chassis is designed for stacking pairs. In the US it remains the cheapest entry to the family at $3,099.99.
vs its siblings: Cheapest US entry; TAA public-sector SKU; stack-friendly chassis.
Memory, to scale
128 GB model-visible · bandwidth is the speed limit
Unified LPDDR5x
128 GB · 273 GB/s
LPDDR5x
For scale
DGX Spark — 128 GB @ 273 GB/s
RTX PRO 6000 — 96 GB @ 1.79 TB/s
Mac Studio M3 Ultra — 512 GB @ 819 GB/s
DGX Station GB300 — 748 GB coherent
Two units link directly over ConnectX-7 to serve ~405B-parameter models.
What it actually runs
Declared from research and benchmarks, not computed marketing — tokens-per-second figures are cited where a real measurement exists.
- gpt-oss-120bMXFP4 nativewith headroom~35–40 tok/s (llama.cpp, verified)
- Qwen3.5 122BQ4with headroom10B active — the quality sweet spot at this size
- Nemotron 3 SuperNVFP4with headroomNVIDIA's own stack, 1M context
- DeepSeek V4 FlashINT4 (community)fits~95 GB weights — thin context headroom
- Llama-70B-class denseQ4fitsfits, but dense models are bandwidth-starved here
- 405B-classFP42+ units linkedtwo Sparks linked over ConnectX-7
The full sheet
Compute
- Superchip
- NVIDIA GB10 Grace Blackwell
- GPU
- Blackwell architecture — 6,144 CUDA cores, 5th-gen Tensor Cores
- AI performance
- Up to 1 PFLOP (1,000 TOPS) sparse FP4
- CPU
- 20-core Arm — 10× Cortex-X925 + 10× Cortex-A725
- Interconnect
- NVLink-C2C (CPU ↔ GPU, coherent)
Memory
- Unified memory
- 128 GB LPDDR5x, 256-bit
- Bandwidth
- 273 GB/s
- Model capacity
- ~200B params FP4 inference · 70B fine-tuning · 405B with two linked units
Storage
- NVMe
- 1 TB NVMe (PCIe Gen4) base · 4 TB SKU available
Networking & I/O
- Smart NIC
- ConnectX-7, 200 Gb/s total (2× QSFP) — direct 2-unit clustering
- Ethernet / wireless
- 1× 10 GbE RJ-45 · WiFi 7 · BT 5.4
- Ports
- 4× USB4 Type-C · HDMI 2.1a
Software
- OS
- NVIDIA DGX OS 7 (Ubuntu 24.04 base)
- Stack
- NVIDIA AI stack, NGC catalogue, NIM microservices, Blueprints, DGX Spark playbooks
- Licence
- 90-day NVIDIA AI Enterprise included (3-year purchasable)
Where it shines
- Whole 120B-class models resident in one coherent pool
- Full NVIDIA CUDA stack — the same software as the data centre
- Plugs into a normal socket; 1-litre class, near-silent
- Two-unit clustering built in via ConnectX-7
The trade-offs
- 273 GB/s bandwidth caps single-stream speed (~35–40 tok/s on gpt-oss-120b)
- Not a high-concurrency server — one team, not one company
- Arm (aarch64) platform: x86 containers need rebuilding
- Family took a price rise in Feb 2026 — the RAM shortage is live
Buy this box for
Understanding NVIDIA DGX Spark
GB10 Grace Blackwell Superchip
The DGX Spark is NVIDIA's reference design for desk-scale AI, built on the GB10 Grace Blackwell Superchip: a 20-core Arm CPU and a Blackwell GPU sharing 128 GB of unified LPDDR5x memory over NVLink-C2C. Because CPU and GPU see one memory pool, sparse models up to ~200 billion parameters (FP4) load whole — no VRAM juggling — and it fine-tunes up to 70B.
It ships as the NVIDIA Founders Edition and as near-identical partner machines from ASUS, Dell, HP, MSI, Lenovo, Acer and Gigabyte — the same superchip with different storage, support and price. Two units link directly over their ConnectX-7 200 Gb ports to serve ~405B-parameter models. Every box arrives with DGX OS, the NVIDIA AI stack, NIM microservices and a 90-day NVIDIA AI Enterprise licence.
The trade-off is bandwidth: 273 GB/s of LPDDR5x is the tokens-per-second ceiling (gpt-oss-120b runs at ~35–40 tok/s). It is a superb prototyping and small-team inference machine, not a high-concurrency server. Note the family took an official price rise in February 2026 (Founders Edition $3,999 → $4,699) as the memory shortage bit.
Siblings on the same silicon
NVIDIA
DGX Spark Founders Edition
The reference machine: NVIDIA's own champagne-gold 1.2 kg desk supercomputer, 4 TB standard, dual QSFP exposed for clustering.
- Memory
- 128 GB
- Bandwidth
- 273 GB/s
- AI perf
- 1 PFLOP FP4
£4,899 inc VAT
Scan UK, in stock · US MSRP $4,699 (raised from $3,999, Feb 2026)
Lenovo
ThinkStation PGX
The GB10 goes corporate — ThinkStation build quality, Premier support options, and currently the cheapest UK route into the family.
- Memory
- 128 GB
- Bandwidth
- 273 GB/s
- AI perf
- 1 PFLOP FP4
from ~£3,211 inc VAT
1 TB SKU via UK resellers (Ballicom £2,675.58 ex VAT) · 4 TB ~£3,809 inc
Acer
Veriton GN100
4 TB standard at £3,999.99 — the aggressive value pick that held the old price point through the shortage.
- Memory
- 128 GB
- Bandwidth
- 273 GB/s
- AI perf
- 1 PFLOP FP4
£3,999.99 inc VAT
4 TB standard — best £/TB in the family
MSI
EdgeXpert MS-C931
The clustering-friendly build — a QSFP cable in the box on Gen5 SKUs, sold through both retail and industrial channels.
- Memory
- 128 GB
- Bandwidth
- 273 GB/s
- AI perf
- 1 PFLOP FP4
from ~£3,949 inc VAT
idealo best UK price · Ballicom £4,723.33 (4 TB)
Gigabyte
AI TOP ATOM
The GB10 wired into Gigabyte's AI TOP tuning ecosystem — a neat 1-litre box with 4 TB Gen5 storage.
- Memory
- 128 GB
- Bandwidth
- 273 GB/s
- AI perf
- 1 PFLOP FP4
£4,858.99 inc VAT
Scan UK, in stock · US $3,999.99 (Newegg)
HP
ZGX Nano AI Station G1n
The Z-workstation take on the GB10 — enterprise support and a family ladder that leads up to the ZGX Fury.
- Memory
- 128 GB
- Bandwidth
- 273 GB/s
- AI perf
- 1 PFLOP FP4
~$4,207 · UK from ~£4,939
US verified (CDW, 4 TB) · UK price indicative only — confirm at quote
Sources & verification
Specifications and prices verified 2026-07 against the sources below. The memory shortage is repricing this market monthly — we re-verify at quote.
Compare against the rest of the catalogue, or have us spec it against your workloads.
Back to catalogueSpec the Ascent GX10 for your workload
We'll size it against your real token volumes, quote supply and lease options, and stand up the models with evals that prove they do the job — or tell you honestly that a different box (or the API) wins.