Mid-Range
Mid-RangeBasic AI Coding
Compact SFF AI Build
$1,473
12 GB VRAM340W TDP~30dB7 components
Inside This Build
Components
| Category | Component | Price | Rationale | Buy |
|---|---|---|---|---|
| gpu |  NVIDIA GeForce RTX 4070 Super 12GB | $599 | 12GB VRAM in compact form. Strong inference for 7–8B models. | |
| cpu |  AMD Ryzen 5 7600 | $199 | 6-core Zen 4. Efficient for SFF, enough for inference. | |
| motherboard | GigabyteGigabyte B650I Aorus Ultra (Mini-ITX) | $219 | Mini-ITX B650 with DDR5. Compact, feature-complete. | |
| ram | 32GB DDR5-5600 (2x16GB) | $79 | 32GB DDR5 for model loading in SFF. | |
| storage | WD1TB WD Black SN850X NVMe | $89 | Fast NVMe. 1TB for models and projects. | |
| psu |  Corsair SF750 750W 80+ Platinum SFX | $139 | SFX form factor. 750W for RTX 4070 Super headroom. | |
| case |  NZXT H1 V2 | $149 | All-in-one SFF with integrated AIO and PSU. Compact footprint. | |
| Total | $1,473 | |||
Shop Components
Search links — prices and availability vary by retailer.
Buy Used GPU
Prices and availability vary. Inspect hardware before purchasing.
What This Runs
AI models tested on this build's hardware.
| Model | Quant | Speed |
|---|---|---|
| Llama 3.1 8B Instruct | Q8_0 | 55 tok/s |
| Qwen 2.5 7B Instruct | Q5_K_M | 45 tok/s |
| Phi-3 Mini 3.8B Instruct | Q8_0 | 65 tok/s |
| Mistral 7B Instruct v0.3 | Q5_K_M | 48 tok/s |
| nomic-embed-text v1.5 | FP16 | — |
Upgrade Path
Swap to RTX 5080 16GB when available in SFF form factors for a major VRAM jump to 16GB.
Target Use Cases
ChatCodingAI Coding
Last updated: 2026-03-01.