The cheapest cataloged machine that runs Gemma 4 on the GPU is a AMD Radeon RX 6700 XT · 12GB VRAM. Here are the most affordable rigs that fit it, smallest memory first.
| machine | best fit | verdict | speed |
|---|---|---|---|
| AMD Radeon RX 6700 XT · 12GB VRAM | 12B Q4_K_M | ✅ Runs (tight) | 14–25 tok/s |
| AMD Radeon RX 7700 XT · 12GB VRAM | 12B Q4_K_M | ✅ Runs (tight) | 16–25 tok/s |
| NVIDIA GeForce RTX 3060 · 12GB VRAM | 12B Q4_K_M | ✅ Runs (tight) | 14–25 tok/s |
| NVIDIA GeForce RTX 4070 · 12GB VRAM | 12B Q4_K_M | ✅ Runs (tight) | 19–30 tok/s |
| AMD Radeon RX 6800 XT · 16GB VRAM | 12B Q6_K | ✅ Runs (tight) | 15–25 tok/s |
| AMD Radeon RX 6950 XT · 16GB VRAM | 12B Q6_K | ✅ Runs (tight) | 17–30 tok/s |
| AMD Radeon RX 7800 XT · 16GB VRAM | 12B Q6_K | ✅ Runs (tight) | 18–30 tok/s |
| NVIDIA GeForce RTX 4080 · 16GB VRAM | 12B Q6_K | ✅ Runs (tight) | 20–35 tok/s |
| NVIDIA GeForce RTX 5080 · 16GB VRAM | 12B Q6_K | ✅ Runs (tight) | 30–50 tok/s |
| AMD Radeon RX 7900 XT · 20GB VRAM | 12B Q8_0 | ✅ Runs (tight) | 19–30 tok/s |
| AMD Radeon RX 7900 XTX · 24GB VRAM | 12B Q8_0 | ✅ Runs comfortably | 25–40 tok/s |
| NVIDIA GeForce RTX 3090 · 24GB VRAM | 12B Q8_0 | ✅ Runs comfortably | 25–40 tok/s |
Already have a machine? See Gemma 4 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 6700 XT verdict here matches what runlocal tells you on the machine.