The cheapest cataloged machine that runs Code Llama on the GPU is a NVIDIA GeForce RTX 3080 · 10GB VRAM. Here are the most affordable rigs that fit it, smallest memory first.
| machine | best fit | verdict | speed |
|---|---|---|---|
| NVIDIA GeForce RTX 3080 · 10GB VRAM | 7B Q5_K_M | ✅ Runs (tight) | 35–60 tok/s |
| AMD Radeon RX 6700 XT · 12GB VRAM | 7B Q5_K_M | ✅ Runs (tight) | 17–30 tok/s |
| AMD Radeon RX 7700 XT · 12GB VRAM | 7B Q5_K_M | ✅ Runs (tight) | 19–30 tok/s |
| NVIDIA GeForce RTX 3060 · 12GB VRAM | 7B Q5_K_M | ✅ Runs (tight) | 16–25 tok/s |
| NVIDIA GeForce RTX 4070 · 12GB VRAM | 7B Q5_K_M | ✅ Runs (tight) | 25–40 tok/s |
| AMD Radeon RX 6800 XT · 16GB VRAM | 13B Q4_K_M | ✅ Runs (tight) | 14–25 tok/s |
| AMD Radeon RX 6950 XT · 16GB VRAM | 13B Q4_K_M | ✅ Runs (tight) | 15–25 tok/s |
| AMD Radeon RX 7800 XT · 16GB VRAM | 13B Q4_K_M | ✅ Runs (tight) | 17–30 tok/s |
| NVIDIA GeForce RTX 4080 · 16GB VRAM | 13B Q4_K_M | ✅ Runs (tight) | 20–35 tok/s |
| NVIDIA GeForce RTX 5080 · 16GB VRAM | 13B Q4_K_M | ✅ Runs (tight) | 25–45 tok/s |
| Apple M3 Pro · 18GB | 7B Q5_K_M | ✅ Runs (tight) | 9–15 tok/s |
| AMD Radeon RX 7900 XT · 20GB VRAM | 34B Q3_K_M | ✅ Runs (tight) | 17–30 tok/s |
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 |
|---|---|---|---|
| 34B | AMD Radeon RX 7900 XT · 20GB VRAM | ✅ Runs (tight) | ~17–30 tok/s (fast) |
| 13B | AMD Radeon RX 6800 XT · 16GB VRAM | ✅ Runs (tight) | ~14–25 tok/s (usable) |
| 7B | NVIDIA GeForce RTX 3080 · 10GB VRAM | ✅ Runs (tight) | ~35–60 tok/s (fast) |
Already have a machine? See Code Llama 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 NVIDIA GeForce RTX 3080 verdict here matches what runlocal tells you on the machine.