Configs › Qwen3.6 27B MTP NVFP4 v3 on Strix Halo: 13.2 tok/s measured
Qwen3.6 27B MTP NVFP4 v3 on Strix Halo: 13.2 tok/s measured
Measured Qwen3.6 27B MTP NVFP4 v3 speeds: 13.2 tok/s on Strix Halo (NVFP4, 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 Qwen3.6 27B MTP NVFP4 v3 on Strix Halo?
- 13.2 tok/s single-stream decode (NVFP4, 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 Qwen3.6 27B MTP NVFP4 v3
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| Qwen3.6 27B MTP NVFP4 v3 | Strix Halo | NVFP4 | llama.cpp/vulkan | 13.2 tok/s (prefill 374) | 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.