Storage holds the download
An SSD keeps model files after shutdown. RAM holds working data while the model runs. Leave free disk space for updates and other models. More SSD space does not replace enough RAM.
ASUS Ascent GX10
Single128 GB GX10 with vLLM for first test; second test used two128 GB GX10s connected over QSFP.
Coding & agentsHome servers
Meet the hardware
Photographs and manufacturer images, with source credits. Select a picture to inspect the full image. The pictured variant may differ from the reviewed unit.
Processor: what does the work?
The CPU keeps the system and applications running. The GPU can do many model calculations together when your engine supports it. More cores do not guarantee a faster answer across different chip families.
Read the right numbers
CPU cores and GPU compute units describe different designs. Compare the same model, engine and settings before treating one chip as faster. An NPU or Neural Engine specification does not prove that your chosen language-model application uses it.
Memory: where the model works
The CPU, GPU and operating system share one memory pool. Shared GPU memory is not extra memory on top of the listed capacity. A large model, a long conversation and other applications all compete for that space.
Capacity is not the same as speed
Capacity tells you how much memory is available. Bandwidth tells you how quickly the chip can read it. A model can fit in memory and still respond slowly. Longer context also uses memory for the model’s working cache.
Learn RAM, VRAM and model size →Storage, connections and upgrades
The unified LPDDR memory is part of the board/platform design, not an ordinary desktop DIMM upgrade. Choose its capacity before purchase. Storage and expansion options depend on this specific chassis.
Connections shape the setup
Check the monitor, network and drive ports you need. USB-C is a connector shape; check its actual speed and display support. A fast network does not automatically merge two computers’ memory.
Detailed system specifications
These are manufacturer product-family specifications and options. The creator’s exact reviewed configuration is listed separately. Confirm the model number and options before buying.
| Specification | Detail | Source |
|---|---|---|
| Cpu | NVIDIA GB10 Arm CPU | Source ↗ |
| Gpu | NVIDIA Blackwell | Source ↗ |
| Memory | 128 GB per tested unit | Source ↗ |
| Memory type | Unified LPDDR5X | Source ↗ |
| Storage | NAS-backed models in review; internal SSD capacity not established | Source ↗ |
| Ports | 10GbE,ConnectX7 QSFP interconnect | Source ↗ |
| Power adaptor output | Up to 240 W (USB-C® PD 3.1 EPR); up to 48V/5A | Source ↗ |
| Device power input (Max.) | 180 W via USB-C® | Source ↗ |
| Size | 150 x 150 x 51 mm (5.91 x 5.91 x 2.01 inches) | Source ↗ |
| Weight | 1.48kg (3.26lb.) | Source ↗ |
Software checks before you start
Confirm your operating system, driver, engine version, model format and quantization. The creator’s named test below is a starting point, not a guarantee that every model or engine works. This is an Arm-based platform. A desktop x86 package is not automatically compatible; use the platform’s documented software stack.
Plan your model and engineWatch the real test
Are Local Models Finally Good Enough?
By Techno Tim · 2026-05-18
Real project workflow exposes capability and setup effort.
What this test does not prove
Cluster tuning and model/cache memory issues required work. Workflow comparison changes both hardware and model; not a controlled speed comparison.
Terms used in this review
A plain-English reading companion for this review and its hardware specifications. Select a term to read its meaning and why it matters. These explanations are not a transcript or quotations from the creator.
27 terms
CPU and CPU cores
The CPU runs the operating system and general instructions. A core is a unit inside it that can work on instructions.
Why it matters here: More cores can help some jobs, but core counts from different chip families are not a shared speed score.
GPU
A graphics processor can do many similar calculations at once. Local AI engines can use that ability to run a model.
Why it matters here: The engine must support the exact GPU and driver. A powerful GPU is not useful to an unsupported engine.
RAM
The computer’s working memory. The operating system, applications and a running model use it.
Why it matters here: A downloaded model can fit on your SSD and still be too large to load into working memory.
VRAM
Memory dedicated to a separate graphics card.
Why it matters here: When a model fits in VRAM with space for its working context, the engine may avoid moving data through slower system memory.
Unified or shared memory
One physical memory pool is shared by the CPU, GPU and the operating system.
Why it matters here: Do not count shared GPU memory as extra RAM. Leave room for the system and other applications.
DDR5, LPDDR5 and LPDDR5X
Names for memory technologies. LPDDR is designed for low-power use and is commonly fitted directly to a board or package.
Why it matters here: The name does not tell you whether you can replace the memory. Check the system’s physical design and upgrade instructions.
DIMM and SO-DIMM
Formats for removable RAM modules. SO-DIMMs are smaller and often used in laptops and mini PCs.
Why it matters here: Do not assume every mini PC has memory slots. Many unified-memory systems use soldered memory instead.
GB/s and Gbps
GB/s means gigabytes per second; Gbps means gigabits per second. A byte contains eight bits.
Why it matters here: A10Gbps network number is not the same as10GB/s of memory bandwidth. Check the units before comparing specifications.
Memory bandwidth
How much data the memory system can move per second. Capacity and bandwidth describe different things.
Why it matters here: A machine may hold a very large model but generate its answers slowly. Check actual model tests.
SSD, NVMe and M.2
An SSD stores files. NVMe is a fast storage protocol. M.2 describes a module and connector format.
Why it matters here: Model downloads live on storage, while a running model needs working memory. Check supported drive sizes and slots before upgrading.
Tokens and tokens per second
A token is a small piece of text. Tokens per second describes how quickly a model produces or processes those pieces.
Why it matters here: Reading the prompt and writing the answer are different measurements. Ask which stage the reviewer measured.
Context window
The amount of text a model can work with at once, including the prompt, conversation and other supplied text.
Why it matters here: A larger setting uses more working memory and can increase loading or response time. Start with enough for your real task.
KV cache
Working memory that keeps information from earlier tokens so the model can use it while continuing an answer.
Why it matters here: Longer context can make this cache larger. Model-file size alone does not describe total memory use.
Quantization and Q4
A way to store model numbers using fewer bits. Q4 usually describes a roughly four-bit approach, with different formats and tradeoffs.
Why it matters here: Lower-bit files often need less memory, but quality and speed can change. Compare the exact file, not just the model name.
Parameters and “B”
Parameters are the model’s learned numbers. B means billion, so 8B means about eight billion parameters.
Why it matters here: More parameters do not guarantee a better result for every task. The model must also fit and respond at a useful speed.
MoE and active parameters
A mixture-of-experts model uses selected parts of the model for each token rather than every part.
Why it matters here: A small active-parameter count does not mean a small download. You still need to account for the stored model and its working memory.
GPU offload
Running some or all of a model’s work on the GPU instead of the CPU.
Why it matters here: Partial offload can allow a model to run, but it is not proof that the complete model fits in the GPU’s memory.
Inference engine
The software that loads a model and performs its calculations to produce an answer.
Why it matters here: The same hardware can behave differently with different engines, drivers and model files.
vLLM
An inference engine often used to serve language models to applications or multiple requests.
Why it matters here: Check supported hardware, number formats and the exact server configuration.
GGUF
A model-file format used by llama.cpp and several local AI applications.
Why it matters here: Choose the model format your engine supports. A downloadable model is not automatically compatible with every application.
CUDA
NVIDIA’s software platform for GPU computing.
Why it matters here: CUDA-based tools need compatible NVIDIA hardware and software. A CUDA tutorial is not an AMD installation guide.
FP8 and FP16
Number formats that use eight or sixteen bits for a stored value.
Why it matters here: Memory use and hardware support differ. A model with the same name but a different format is a different configuration to test.
Time to first token
The wait before the model starts producing its answer.
Why it matters here: A system can write quickly once started but still spend a long time reading a large document first.
RAG
Retrieval-augmented generation: finding relevant passages from documents and supplying them to a model with your question.
Why it matters here: This can help answer from your files, but you still need to check the cited passages and answer accuracy.
TDP and power supply rating
TDP is a chip cooling or power-design figure. The power supply rating is the amount the supply is designed to provide.
Why it matters here: Neither number alone is a measurement of the full system’s electricity use during your AI task.
NPU or Neural Engine
A specialized processor for supported AI workloads.
Why it matters here: An NPU specification does not mean your chosen local language-model engine uses it.
Cluster and multi-node
Two or more computers working together through software and a network.
Why it matters here: More machines do not automatically mean faster answers or one shared memory pool. Check single-machine and cluster results separately.
Further reading: LM Studio load settings · Quantization · KV cache
What the creator tested
These observations belong to this source and configuration. Changing the model file, context or software can change the result.
Qwen3.6-35B-A3B
Engine: vLLM with OpenCode · Quantization: FP8
Single GX10 coding workflow worked with human steering.
Explore this model family and size in our catalog →
The catalog artifact, quantization or variant may differ from the review. This link does not extend the tested result.
MiniMax M2.7
Engine: vLLM/Ray with OpenCode · Quantization: AWQ4bit
Two-node test only; do not present as a single-GX10 result.
No exact family-and-size catalog link recorded. Use the creator’s source for the tested model.
Is it useful for your work?
Choose for CUDA development; budget setup time and verify single-node requirements separately.
Check before buying
- Internal SSD SKU
- Current pricing
Check current price, regional availability, returns, warranty and the exact memory configuration with the seller. This guide does not guarantee a specific speed.
Community and reproducibility
No separately verified owner report is attached to this profile yet. The creator test above is the evidence currently recorded.
Have this hardware? Share the exact model file, engine version, memory, context length, speed and any setup problems.
Contribute your testMatch the exact configuration
Check memory, storage, model number, seller warranty, returns and shipping to your country. A product-family name does not identify every component inside.
View manufacturer options ↗