Nex-N2.5-mini 35B · 3B active at 4-bit generates a median of 76.9 tokens per second on the AMD Strix Halo 128GB, the hardware it is most run on, from one plain run (community reports, as of 25 Oct 2026).
As of 25 Oct 2026, Nex-N2.5-mini 35B · 3B active at 4-bit on the hardware it is most run on, with the median of plain runs (one device, one request, no speculative decoding, the whole model in its memory):
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is shown only when the source reports it; generation speed cannot tell us time to first token. Check the full setup before comparing.
agenticcoding
User reports Nex-N2.5-mini at 133.6 t/s on an Apple M5 Max.
Setup is MLX with the MLX-4bit quant, using temperature 0.7, top_p 0.95, top_k 40, and reasoning_effort high.
User calls the generation speed and prompt processing really good, the memory footprint okay, and the quality good across the board, and plans to use it for agents and possibly coding.
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is shown only when the source reports it; generation speed cannot tell us time to first token. Check the full setup before comparing.
User benchmarks Nex-N2.5-mini in ROCmFP4 GGUF on AMD Strix Halo against Qwen3.8-27B, decoding at 76.9 t/s versus 14-34 t/s.
Setup is the HaloFPX engine with weights from julianmb/Nex-N2.5-mini-ROCmFP4-GGUF.
Nex-N2.5-mini scores 73.4 on Terminal-Bench 2.1 against 73.0, 63.4 on WebArena against 64.8, and 43.8 on SWE-Bench against 61.7.
Get a weekly email of new Nex-N2.5-mini reports on any GPU.
Individual observations from this page, not expected speeds or a ranking. Select a model to open its report, with the source and offloading conditions. Reported context may be a limit rather than actual input length.
The hardware Nex-N2.5-mini 35B · 3B active at 4-bit is most run on: AMD Strix Halo 128GB (76.9 t/s median, one run); M5 Max 128GB (133.6 t/s median, one run). Medians of plain runs, as of 25 Oct 2026.
Which inference engines do people use for Nex-N2.5-mini?
Reports of Nex-N2.5-mini name MLX (1 report), as of 25 Oct 2026.
Speed by hardware on Nex-N2.5-mini 35B · 3B active at 4-bit
The size and quant level the most devices have plain runs of: one device, one request, no speculative decoding, and the whole model in the device's memory. Every speed in this table is the same model.