community-verified · measured pool data
Can the RX 7900 XTX 24GB run Qwen3.5-9B-MTP-GGUF?
Yes — community-measured at 154.4 tok/s (2 runs at 6-bit).
Verified single-stream runs on the RX 7900 XTX 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 |
|---|---|---|---|---|---|
| 6-bit | 154.4 | — | 16.2 GB | 262,144 | llama.cpp |