community-verified · measured pool data
Can the RTX 3090 24GB run GLM-Z1-32B-0414?
Yes — community-measured at 21.6 tok/s (10 runs at 4-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 |
|---|---|---|---|---|---|
| 4-bit | 21.6 | 5986.3 | — | 131,072 | llama.cpp |