Configs › Qwen3-Coder-Next on Strix Halo: 50 tok/s measured
Qwen3-Coder-Next on Strix Halo: 50 tok/s measured
Measured Qwen3-Coder-Next speeds: 50 tok/s on Strix Halo (Q4_K_M). 1 config, each linked to its source, snapshot 2026-10-05.
Snapshot 2026-10-05 · 258 configs · 118 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-Coder-Next on Strix Halo?
- 50 tok/s single-stream decode (Q4_K_M), the only measured config on AMD Strix Halo (Ryzen AI Max+ 395), measured by YauhenBichel, source last checked 2026-10-03. source
Measured configs for Qwen3-Coder-Next
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| Qwen3-Coder-Next | Strix Halo | Q4_K_M | 50 tok/s (prefill 590) | 64000 | Extracted, source-linked | 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.