What hardware runs Gemma 3?

The smallest-memory cataloged machine that runs Gemma 3 on the GPU is a Apple M1 · 8GB. Here are the rigs that fit it, smallest memory first.

machine	best fit	verdict	speed
Apple M1 · 8GB	1B Q8_0	✅ Runs comfortably	40–65 tok/s
Apple M2 · 8GB	1B Q8_0	✅ Runs comfortably	60–95 tok/s
Apple M3 · 8GB	1B Q8_0	✅ Runs comfortably	60–95 tok/s
AMD Radeon RX 7600 · 8GB VRAM	4B Q8_0	✅ Runs (tight)	25–40 tok/s
NVIDIA GeForce RTX 3070 · 8GB VRAM	4B Q8_0	✅ Runs (tight)	40–65 tok/s
NVIDIA GeForce RTX 4060 · 8GB VRAM	4B Q8_0	✅ Runs (tight)	25–40 tok/s
NVIDIA GeForce RTX 3080 · 10GB VRAM	4B Q8_0	✅ Runs comfortably	70–120 tok/s
AMD Radeon RX 6700 XT · 12GB VRAM	12B Q4_K_M	✅ Runs (tight)	20–35 tok/s
AMD Radeon RX 7700 XT · 12GB VRAM	12B Q4_K_M	✅ Runs (tight)	20–35 tok/s
NVIDIA GeForce RTX 3060 · 12GB VRAM	12B Q4_K_M	✅ Runs (tight)	20–35 tok/s
NVIDIA GeForce RTX 4070 · 12GB VRAM	12B Q4_K_M	✅ Runs (tight)	25–45 tok/s
Apple M1 · 16GB	4B Q8_0	✅ Runs comfortably	9–15 tok/s

Minimum rig by size

The smallest cataloged machine that runs each size on the GPU (default 8K context). Bigger sizes need more memory — a rig that runs the small one may not touch the large.

size	minimum rig	verdict	speed
27B	AMD Radeon RX 7900 XT · 20GB VRAM	✅ Runs (tight)	~25–40 tok/s (fast)
12B	AMD Radeon RX 6700 XT · 12GB VRAM	✅ Runs (tight)	~20–35 tok/s (fast)
4B	AMD Radeon RX 7600 · 8GB VRAM	✅ Runs (tight)	~25–40 tok/s (fast)
1B	AMD Radeon RX 7600 · 8GB VRAM	✅ Runs comfortably	~110–180 tok/s (very fast)

Already have a machine? See Gemma 3 across popular rigs → or check your exact rig →

Planning a whole workflow? Rigs for a coding agent · local chat · reasoning · local RAG setup.

$npx runlocal-sh can-i-run gemma3 --hardware <your-rig>

Verdicts use the same GQA-aware fit math as the CLI — a Apple M1 verdict here matches what runlocal tells you on the machine.