The cheapest cataloged machine that runs Nemotron-Mini 4B on the GPU is a AMD Radeon RX 7600 · 8GB VRAM. Here are the most affordable rigs that fit it, smallest memory first.
| machine | best fit | verdict | speed |
|---|---|---|---|
| AMD Radeon RX 7600 · 8GB VRAM | 4B Q8_0 | ✅ Runs comfortably | 20–35 tok/s |
| NVIDIA GeForce RTX 3070 · 8GB VRAM | 4B Q8_0 | ✅ Runs comfortably | 35–60 tok/s |
| NVIDIA GeForce RTX 4060 · 8GB VRAM | 4B Q8_0 | ✅ Runs comfortably | 20–35 tok/s |
| NVIDIA GeForce RTX 3080 · 10GB VRAM | 4B Q8_0 | ✅ Runs comfortably | 60–100 tok/s |
| AMD Radeon RX 6700 XT · 12GB VRAM | 4B Q8_0 | ✅ Runs comfortably | 30–50 tok/s |
| AMD Radeon RX 7700 XT · 12GB VRAM | 4B Q8_0 | ✅ Runs comfortably | 30–55 tok/s |
| NVIDIA GeForce RTX 3060 · 12GB VRAM | 4B Q8_0 | ✅ Runs comfortably | 30–45 tok/s |
| NVIDIA GeForce RTX 4070 · 12GB VRAM | 4B Q8_0 | ✅ Runs comfortably | 40–65 tok/s |
| AMD Radeon RX 6800 XT · 16GB VRAM | 4B Q8_0 | ✅ Runs comfortably | 40–65 tok/s |
| AMD Radeon RX 6950 XT · 16GB VRAM | 4B Q8_0 | ✅ Runs comfortably | 45–70 tok/s |
| AMD Radeon RX 7800 XT · 16GB VRAM | 4B Q8_0 | ✅ Runs comfortably | 45–80 tok/s |
| Apple M1 · 16GB | 4B Q8_0 | ✅ Runs comfortably | 8–13 tok/s |
Already have a machine? See Nemotron-Mini 4B across popular rigs → or check your exact rig →
Planning a whole workflow? Rigs for a coding agent · local chat · reasoning · local RAG setup.
Verdicts use the same GQA-aware fit math as the CLI — a AMD Radeon RX 7600 verdict here matches what runlocal tells you on the machine.