community-verified · measured pool data
Can the RTX 3090 24GB run Bonsai-27B-gguf?
Yes — community-measured at 39.8 tok/s (11 runs at 1-bit).
Verified single-stream runs on the RTX 3090 24GB from the localmaxxing public pool. Every number on this page is measured — nothing here is estimated.
| Quantization | Median tok/s | TTFT (ms) | Peak VRAM | Max context tested | Engines |
|---|---|---|---|---|---|
| 1-bit | 39.8 | 31904.2 | 5.6 GB | 262,144 | llama.cpp |