community-verified · measured pool data
Can the RTX 5070 Ti 16GB run LFM2.5-8B-A1B?
Yes — community-measured at 307.4 tok/s (2 runs at 8-bit).
Verified single-stream runs on the RTX 5070 Ti 16GB 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 |
|---|---|---|---|---|---|
| 8-bit | 307.4 | 19.5 | — | 4,096 | llama.cpp |