MINIX N304-AI (Intel Core 3 304, Wildcat Lake)
MINIX · Mini PC · Released 2026Verified 2026-07-21
— GB
LPDDR5X (16 GB, shared CPU/GPU/NPU)
—
NPU TOPS
—
GB/s Bandwidth
35 W
TDP
— GBMemory (LPDDR5X (16 GB, shared CPU/GPU/NPU))
— GB/sMemory Bandwidth
—NPU TOPS
—GPU Compute Units
—CPU Cores
35 WTDP
AI Workload Fit
Local LLM Inference
Not recommended — No models fit
⚠ Limited
Image Generation
Requires more memory
✗ Not fit
NPU/AI Acceleration
No NPU — 0 TOPS
✗ None
Power Efficiency
Excellent — 35W TDP
✓ Efficient
Model Fit Analysis
Usable AI memory: 0 GB (OS reserve: 2GB, GPU allocation: 75%) Conservative
Maximum model size at Q4: No models fit (0B params, ~0GB 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
✗ Too large
Llama 3.1 70B
~37.14GB Q4
✗ Too large
Llama 3.2 1B
~2GB Q4
✗ Too large
Llama 3.2 3B
~3.01GB Q4
✗ Too large
Qwen 2.5 7B
~5.01GB Q4
✗ Too large
Qwen 2.5 14B
~8.53GB Q4
✗ Too large
Qwen 2.5 32B
~18.06GB Q4
✗ Too large
Qwen 2.5 72B
~38.14GB Q4
✗ Too large
Mistral 7B
~5.01GB Q4
✗ Too large
Mixtral 8x7B
~25.44GB Q4
✗ Too large
DeepSeek R1 7B
~5.01GB Q4
✗ Too large
DeepSeek R1 32B
~18.06GB Q4
✗ Too large
DeepSeek R1 70B
~37.14GB Q4
✗ Too large
Phi-3 Medium 14B
~8.53GB Q4
✗ Too large
Gemma 2 9B
~6.02GB Q4
✗ Too large
Gemma 2 27B
~15.05GB Q4
✗ Too large
Stable Diffusion XL
~4.81GB Q4
✗ Too large
Flux.1 Dev
~7.52GB Q4
✗ Too large
Flux.1 Schnell
~7.52GB Q4
✗ Too large
Full Specifications
| Specification | Value |
|---|---|
| Memory Type | LPDDR5X (16 GB, shared CPU/GPU/NPU) https://www.minix.com.hk/blogs/blog-center/n304-ai-brings-ai-computing |
| Pcie Interface | PCIe 4.0, up to 6 lanes; Thunderbolt 4; eDP 1.5, DP 2.1 HBR3, HDMI 2.0b https://www.minix.com.hk/blogs/blog-center/n304-ai-brings-ai-computing |
| Tdp Watts | 35 https://www.minix.com.hk/blogs/blog-center/n304-ai-brings-ai-computing |
| Vram Gb | 16 https://www.minix.com.hk/blogs/blog-center/n304-ai-brings-ai-computing |
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