Open Models Almanac
Methodsinference & servingdecoding strategy

specific method · filed under inference & serving

NEXTN speculative decoding

A serving-exposed speculative-decoding mode using a multi-step-trained MTP head or draft tokens.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See decoding strategy for the methods filed beside it.

Also called native NEXTN speculative decoding, NEXTN speculative decoding algorithm, NEXTN.

sources
4
models
3
labs adopt it
2
strongest
used

Documented in

Tencent (Hunyuan)

Evidence

4 quotes from 4 sources, one card per model, each opening with its strongest.

How sources treat it
optional 2used 2

Qwen3.5-397B-A17B

Alibaba (Qwen)adopted2 sources

--speculative-algo NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4

optionalinference servingin Qwen3.5-122B-A10BQwen Team
1 more from this model

--speculative-algo NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4

optionalinference servingin Qwen3.5-35B-A3BQwen Team
↑