What hardware runs Llama 3.1?

The cheapest cataloged machine that runs Llama 3.1 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	8B Q5_K_M	✅ Runs (tight)	17–30 tok/s
NVIDIA GeForce RTX 3070 · 8GB VRAM	8B Q5_K_M	✅ Runs (tight)	25–45 tok/s
NVIDIA GeForce RTX 4060 · 8GB VRAM	8B Q5_K_M	✅ Runs (tight)	17–30 tok/s
NVIDIA GeForce RTX 3080 · 10GB VRAM	8B Q6_K	✅ Runs (tight)	40–70 tok/s
AMD Radeon RX 6700 XT · 12GB VRAM	8B Q8_0	✅ Runs (tight)	16–25 tok/s
AMD Radeon RX 7700 XT · 12GB VRAM	8B Q8_0	✅ Runs (tight)	18–30 tok/s
NVIDIA GeForce RTX 3060 · 12GB VRAM	8B Q8_0	✅ Runs (tight)	15–25 tok/s
NVIDIA GeForce RTX 4070 · 12GB VRAM	8B Q8_0	✅ Runs (tight)	20–35 tok/s
AMD Radeon RX 6800 XT · 16GB VRAM	8B Q8_0	✅ Runs comfortably	20–35 tok/s
AMD Radeon RX 6950 XT · 16GB VRAM	8B Q8_0	✅ Runs comfortably	25–40 tok/s
AMD Radeon RX 7800 XT · 16GB VRAM	8B Q8_0	✅ Runs comfortably	25–45 tok/s
NVIDIA GeForce RTX 4080 · 16GB VRAM	8B Q8_0	✅ Runs comfortably	30–55 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
70B	NVIDIA GeForce RTX 5090 · 32GB VRAM	✅ Runs (tight)	~25–40 tok/s (fast)
8B	AMD Radeon RX 7600 · 8GB VRAM	✅ Runs (tight)	~17–30 tok/s (fast)

Already have a machine? See Llama 3.1 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 llama-3.1 --hardware <your-rig>

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.