Can I run this LLM?
Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Ternary Bonsai 2 27B?
Bonsai · Apache 2.0 · estimated for a 144.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Ternary Bonsai 2 27B at PQ2_0 · 7.2 GB · 189–284 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| PTQ1_0 | 6.0 GB | 194–291 tok/s | Runs great |
| PQ2_0 | 7.2 GB | 189–284 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) runsTernary Bonsai 2 27B on other machinesWhat to buy to run it →
Ran Ternary Bonsai 2 27B on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →