Can I run this LLM?
Can a AMD RX 9070 (16GB) run Laguna XS 2.1 (MoE)?
Laguna · openmdw-1.1 · estimated for a 16.0 GB machine at 4K context.
Yes, but it's tight.
Best fit: Laguna XS 2.1 (MoE) at Q2_K · 12.2 GB · 156–234 tok/s on a AMD RX 9070 (16GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 12.2 GB | 156–234 tok/s | Tight / slow |
| Q3_K_M | 15.6 GB | 142–212 tok/s | Won't fit |
| Q4_K_M | 20.6 GB | 125–187 tok/s | Won't fit |
| Q5_K_M | 24.0 GB | 116–173 tok/s | Won't fit |
| Q6_K | 29.0 GB | 104–156 tok/s | Won't fit |
| Q8_0 | 35.6 GB | 92–138 tok/s | Won't fit |
| FP16 | 66.9 GB | 60–90 tok/s | Won't fit |
Open the full calculator →Everything a AMD RX 9070 (16GB) runsLaguna XS 2.1 (MoE) on other machinesWhat to buy to run it →
Ran Laguna XS 2.1 (MoE) on a AMD RX 9070 (16GB)? Add your real numbers →