Can I run this LLM?
Can a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB) run 1-bit Bonsai 27B?
Bonsai · Apache 2.0 · estimated for a 288.0 GB machine at 4K context.
Yes — it runs great.
Runs greatBest fit: 1-bit Bonsai 27B at Q1_0 · 3.8 GB weights · 271–407 tok/s on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB).
Only the shipped native packs are available. Pack preference does not establish measured output quality. The trained context limit is 256K tokens. These estimates use 4K context.
Arena Text Overall · style-controlled
UnratedNo exact matchNo reviewed exact Arena match
No reviewed exact model/configuration match in the Arena Text Overall style-controlled snapshot. No family or editorial score is substituted. Local quantization quality is unmeasured.
Snapshot published 2026-10-08 · snapshot imported 2026-10-11 UTC · validated last-good data · manual refresh
Arena leaderboard dataset · Arena / lmarena-ai, Arena Leaderboard Dataset (CC BY 4.0). Selected Text Overall style-controlled rows; field names adapted, ratings unchanged. · dataset CC BY 4.0 · revision e16f90232986
- Total memory at 4K context
- 4.9 GB
- Weights + KV cache + runtime overhead
- Estimated generation
- 271–407 tok/s
- Estimated first token
- ~0.5s
Every quantization on this machine
On small screens, each quant lists every metric below its name. On wider screens, scroll sideways for total memory, speed and fit. Keyboard: focus the table, then use the arrow keys. Quant names stay visible.
| Quant | Weights | Total memory | Speed | Fit |
|---|---|---|---|---|
| Q1_0 | 3.8 GB | 4.9 GB | 271–407 tok/s | Runs great |
Ran 1-bit Bonsai 27B on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB)? Add your real numbers →