Configs › Gemma 4 12B IT QAT on Strix Halo: 29.3 tok/s measured
Gemma 4 12B IT QAT on Strix Halo: 29.3 tok/s measured
Measured Gemma 4 12B IT QAT speeds: 29.3 tok/s on Strix Halo (UD-Q4_K_XL, llama.cpp/vulkan). 1 config, each linked to its source, snapshot 2026-10-16.
Snapshot 2026-10-16 · 394 configs on AI boxes and 423 on GPU cards · 123 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.
Quick answers
- How fast is Gemma 4 12B IT QAT on Strix Halo?
- 29.3 tok/s single-stream decode (UD-Q4_K_XL, llama.cpp/vulkan), the only measured config on AMD Strix Halo (Ryzen AI Max+ 395), measured by hogeheer, source last checked 2026-10-16. source
Measured configs for Gemma 4 12B IT QAT
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| Gemma 4 12B IT QAT | Strix Halo | UD-Q4_K_XL | llama.cpp/vulkan | 29.3 tok/s (prefill 816.3) | 512 | Structured table | source |
More: all configs · hardware · news · contributors · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.