The smallest-memory cataloged machine that runs Phi-3.5-mini on the GPU is a AMD Radeon RX 7600 · 8GB VRAM. Here are the rigs that fit it, smallest memory first.
| machine | best fit | verdict | speed |
|---|---|---|---|
| AMD Radeon RX 7600 · 8GB VRAM | 3.8B Q5_K_M | ✅ Runs (tight) | 40–65 tok/s |
| NVIDIA GeForce RTX 3070 · 8GB VRAM | 3.8B Q5_K_M | ✅ Runs (tight) | 65–110 tok/s |
| NVIDIA GeForce RTX 4060 · 8GB VRAM | 3.8B Q5_K_M | ✅ Runs (tight) | 40–65 tok/s |
| NVIDIA GeForce RTX 3080 · 10GB VRAM | 3.8B Q8_0 | ✅ Runs (tight) | 75–120 tok/s |
| AMD Radeon RX 6700 XT · 12GB VRAM | 3.8B Q8_0 | ✅ Runs comfortably | 35–60 tok/s |
| AMD Radeon RX 7700 XT · 12GB VRAM | 3.8B Q8_0 | ✅ Runs comfortably | 40–70 tok/s |
| NVIDIA GeForce RTX 3060 · 12GB VRAM | 3.8B Q8_0 | ✅ Runs comfortably | 35–60 tok/s |
| NVIDIA GeForce RTX 4070 · 12GB VRAM | 3.8B Q8_0 | ✅ Runs comfortably | 50–85 tok/s |
| AMD Radeon RX 6800 XT · 16GB VRAM | 3.8B Q8_0 | ✅ Runs comfortably | 50–85 tok/s |
| AMD Radeon RX 6950 XT · 16GB VRAM | 3.8B Q8_0 | ✅ Runs comfortably | 55–95 tok/s |
| AMD Radeon RX 7800 XT · 16GB VRAM | 3.8B Q8_0 | ✅ Runs comfortably | 60–100 tok/s |
| NVIDIA GeForce RTX 4080 · 16GB VRAM | 3.8B Q8_0 | ✅ Runs comfortably | 75–120 tok/s |
Already have a machine? See Phi-3.5-mini 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.