Configs › Nex N2.5 Mini 35B-A3B › Nex N2.5 Mini 35B-A3B on Strix Halo: 76.9 tok/s, 3 measured configs
Nex N2.5 Mini 35B-A3B on Strix Halo: 76.9 tok/s, 3 measured configs
Measured Nex N2.5 Mini 35B-A3B speeds on Strix Halo: fastest 76.9 tok/s single-stream (FP4), 3 configs with quant, backend and context, each linked to its source, snapshot 2026-10-29.
Snapshot 2026-10-29 · 413 configs on AI boxes and 288 on GPU cards · 121 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.
Fastest measured single-stream run of Nex N2.5 Mini 35B-A3B on Strix Halo: 76.9 tok/s (FP4), snapshot 2026-10-29.
Every measured single-stream run of Nex N2.5 Mini 35B-A3B on Strix Halo
| Decode tok/s | Quant | Backend | Context | Trust | Measured by | Source checked | Source |
|---|---|---|---|---|---|---|---|
| 76.9 | FP4 | Owner-submitted | julianmb | 2026-09-10 | source | ||
| 72.8 | Q4_K_M | Owner-submitted | julianmb | 2026-09-10 | source | ||
| 50.8 | Q4_K_M | ollama | Extracted, source-linked | huppiflupp | 2026-10-24 | source |
Best quant on Strix Halo
Fastest plain-decoding run per quant, versus the fastest quant.
- FP4: 76.9 tok/s, fastest ()
- Q4_K_M: 72.8 tok/s, 5% lower ()
Questions and answers
- How fast is Nex N2.5 Mini 35B-A3B on Strix Halo?
- The fastest of 3 measured configs is 76.9 tok/s single-stream (FP4). The slowest is 50.8 tok/s.
- Which quant of Nex N2.5 Mini 35B-A3B is fastest on Strix Halo?
- FP4 at 76.9 tok/s, ahead of Q4_K_M at 72.8. Plain decoding only.
See also: Nex N2.5 Mini 35B-A3B on every box · Strix Halo hardware page (from S$4,329 in Singapore today).
Last updated: snapshot 2026-10-29; newest source check 2026-10-24.
More: all configs · hardware · news · contributors · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.