KAMRUI Pinova P2 Mini PC (AMD Ryzen 4300U)
The KAMRUI Pinova P2 is a compact silver AMD mini PC for entry-level local AI inference. Powered by the Ryzen 4300U with 16GB LPDDR4 and 512GB SSD, it runs 7B LLMs via Ollama and supports triple 4K display output — all in a compact silver chassis at a budget-friendly price.
MEMORY
16 GB
BANDWIDTH
34 GB/s
TDP
28W
MAX MODEL
13B (Q4 quantized)
Running Llama 3.2 3B on the KAMRUI Pinova P2: The Cheapest Local AI Entry Point
What Can You Run on This?
- Budget local LLM inference (7B models via Ollama)
- Private offline AI assistant for home or office
- Triple 4K display desktop replacement
- Windows 11 Pro lightweight productivity workstation
- Entry-level AI tinkering and experimentation
Full Specifications
| Chip / Processor | AMD Ryzen 3 4300U (Zen 2, 4C/4T) |
|---|---|
| CPU Cores | 4 |
| GPU Cores | 6 |
| Unified Memory?Unified MemoryApple Silicon uses a single pool of fast RAM shared between CPU and GPU. Larger unified memory = larger models run entirely at full bandwidth — no PCIe bottleneck. | 16 GB |
| Memory Bandwidth?Memory BandwidthHow fast data moves between memory and the processor, measured in GB/s. Tokens per second scales nearly linearly with bandwidth — this is the single most important GPU spec for LLM speed. | 34 GB/s |
| Storage | 512 GB |
| TDP (Power Draw)?TDP (Power Draw)Thermal Design Power in watts — the maximum sustained power draw. Higher TDP generally means more performance but more heat and electricity cost. Important for 24/7 always-on setups. | 28W |
| Max LLM Size?Max LLM SizeThe largest language model this hardware can run with full GPU/unified-memory acceleration, at the specified quantization. Larger models require more memory. | 13B (Q4 quantized) |
| Form Factor | Mini PC |
| AI Performance Benchmarks | |
| Tokens Per Second (7B) | 9 t/s |
Pros & Cons
Pros
- Silver premium-looking design at a budget price
- 16GB LPDDR4 — enough for 7B models and light 13B Q4 inference
- Triple 4K display via HDMI + DP + USB-C Type-C
- 28W TDP — quiet and energy-efficient for always-on use
- Compact footprint — fits on any desk or behind a monitor
Cons
- Ryzen 4300U is a 2020 Zen 2 chip — older architecture than competitors
- Vega 5 iGPU too weak for meaningful AI GPU acceleration
- 34 GB/s memory bandwidth limits LLM tokens-per-second
- LPDDR4 is soldered — not upgradeable unlike some SO-DIMM competitors
Who Should NOT Buy This
Honest assessment
- Real-time chat — 9 t/s is below the interactive threshold
- Running models larger than 7B comfortably — 16 GB is the hard ceiling
- Stable Diffusion — no GPU
- Primary workstation — the N150 processor is efficient, not powerful
Our Verdict
KAMRUI Pinova P2 Mini PC (AMD Ryzen 4300U)
The KAMRUI Pinova P2 occupies the budget tier alongside the P1 — same Ryzen 4300U chip, different chassis. The silver design is a nice touch. At 5–8 tokens/second for 7B models, it is not fast, but it runs privately and locally without a subscription. Choose the Hyper H2 if you need more speed; choose the P2 if budget and aesthetics are the priority.
Frequently Asked Questions
Q1Can the KAMRUI Pinova P2 run local LLMs?
Yes. Using Ollama on Windows 11 Pro, the Pinova P2 runs Llama 3.1 8B at approximately 5–8 tokens/second via the Ryzen 4300U CPU. 13B Q4 models run at 3–5 tokens/second. This is functional for offline chatbot use but noticeably slower than Intel Core 14450HX alternatives.
Q2What is the difference between the KAMRUI Pinova P1 and P2?
The P1 and P2 use the same AMD Ryzen 4300U processor and 16GB RAM. The main difference is the chassis: the P1 has a black design with orange accents, while the P2 has a silver aluminium-style chassis. Performance is identical. Choose based on your preferred aesthetic.
Don't Bottleneck Your Rig
Accessories that unlock this hardware's full potential
Also Featured In
Compare With
As an Amazon Associate I earn from qualifying purchases.
KAMRUI Pinova P2 Mini PC (AMD Ryzen 4300U)
Check Price on Amazon