ASUS Ascent QN10
ASUS · Mini PC · Released 2026Verified 2026-07-21
32 GB
LPDDR5x 8533/9600MHz
80
NPU TOPS
—
GB/s Bandwidth
— W
TDP
32 GBMemory (LPDDR5x 8533/9600MHz)
— GB/sMemory Bandwidth
80NPU TOPS
—GPU Compute Units
—CPU Cores
— WTDP
MSRP: $1,699
Sourced MSRP · Verified 2026-07-21
No current affiliate offer available. Check retailer directly.
AI Workload Fit
Local LLM Inference
Good — 34B class models
✓ Capable
Image Generation
SDXL, Flux
✓ Capable
NPU/AI Acceleration
Strong NPU — 80 TOPS
✓ Strong
Power Efficiency
Good — ?W TDP
⚠ Moderate
Model Fit Analysis
Usable AI memory: 22.5 GB (OS reserve: 2GB, GPU allocation: 75%) Conservative
Maximum model size at Q4: 34B class models (38B params, ~76GB at FP16)
Method: amd_igpu_bios_limited. Estimates account for OS reserve, GPU memory allocation fraction, and memory architecture. Actual results vary by workload, BIOS settings, and model architecture.
Llama 3.1 8B
~5.52GB Q4
✓ Fits
Llama 3.1 70B
~37.14GB Q4
✗ Too large
Llama 3.2 1B
~2GB Q4
✓ Fits
Llama 3.2 3B
~3.01GB Q4
✓ Fits
Qwen 2.5 7B
~5.01GB Q4
✓ Fits
Qwen 2.5 14B
~8.53GB Q4
✓ Fits
Qwen 2.5 32B
~18.06GB Q4
✓ Fits
Qwen 2.5 72B
~38.14GB Q4
✗ Too large
Mistral 7B
~5.01GB Q4
✓ Fits
Mixtral 8x7B
~25.44GB Q4
✗ Too large
DeepSeek R1 7B
~5.01GB Q4
✓ Fits
DeepSeek R1 32B
~18.06GB Q4
✓ Fits
DeepSeek R1 70B
~37.14GB Q4
✗ Too large
Phi-3 Medium 14B
~8.53GB Q4
✓ Fits
Gemma 2 9B
~6.02GB Q4
✓ Fits
Gemma 2 27B
~15.05GB Q4
✓ Fits
Stable Diffusion XL
~4.81GB Q4
✓ Fits
Flux.1 Dev
~7.52GB Q4
✓ Fits
Flux.1 Schnell
~7.52GB Q4
✓ Fits
Full Specifications
| Specification | Value |
|---|---|
| Memory Gb | 32 https://www.asus.com/displays-desktops/mini-pcs/ascent-series/asus-ascent-qn10/techspec/ |
| Memory Type | LPDDR5x 8533/9600MHz https://www.asus.com/displays-desktops/mini-pcs/ascent-series/asus-ascent-qn10/techspec/ |
| Npu Tops | 80 https://www.asus.com/displays-desktops/mini-pcs/ascent-series/asus-ascent-qn10/techspec/ |
Compare with Other Mini PCs
Popular Comparisons
Specifications sourced from manufacturer datasheets. MSRP verified 2026-07-21. Model-fit uses conservative estimates accounting for OS reserve and GPU allocation — actual performance varies. Methodology