Can I run this LLM?
Can a AMD Instinct MI300X (192GB) run Llama 3.3 70B Instruct?
Llama · Llama 3.3 Community · estimated for a 192.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Llama 3.3 70B Instruct at FP16 · 141.1 GB · 26–38 tok/s on a AMD Instinct MI300X (192GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 26.4 GB | 102–153 tok/s | Runs great |
| Q3_K_M | 34.3 GB | 85–127 tok/s | Runs great |
| Q4_K_M | 42.5 GB | 72–108 tok/s | Runs great |
| Q5_K_M | 50.0 GB | 63–95 tok/s | Runs great |
| Q6_K | 57.9 GB | 56–84 tok/s | Runs great |
| Q8_0 | 75.0 GB | 45–67 tok/s | Runs great |
| FP16 | 141.1 GB | 26–38 tok/s | Runs great |
Open the full calculator →Everything a AMD Instinct MI300X (192GB) runsLlama 3.3 70B Instruct on other machinesWhat to buy to run it →
Ran Llama 3.3 70B Instruct on a AMD Instinct MI300X (192GB)? Add your real numbers →