GoKawiilNeutrino-1 0.6B drafts a run of tokens, the 8B scores the whole run in one forward pass, and the agreeing prefix is kept. A draft token is accepted only when it equals the 8B's own argmax, so the output stream is the plain greedy stream: on the shipping configuration, 27,648 consecutive tokens matched with zero divergences.
The speedup is draft-acceptance physics, so it is stated per prompt class over the 396 tok/s plain rate. On counting prompts the 8B accepts the full six-token draft on every pass, about seven tokens emitted per 8B forward; on factual prompts acceptance holds at 96.5%. A dynamic controller sizes each draft to the class it is decoding, which is why every class clears the plain rate.
Counting and lists 763 tok/s ×1.93 Factual short answers 613 tok/s ×1.55 Prose continuation 532 tok/s ×1.34 Conversational explanation 447 tok/s ×1.13 Code 426 tok/s ×1.07 H100, three-round median per prompt class, over 396 tok/s plain decode.
What the pairing costs
Both containers are the same format and run on the same binaries, so the draft loads into the verifier's own process with no second deployment and no conversion step. Its 328 MB sit beside the 8B's 3.88 GB, and 4k tokens of shared context cost exactly one gibibyte of cache across the pair.
one process, one set of binaries Neutrino-1 8B 3.88 GB, verifier Neutrino-1 0.6B 328 MB, draft six proposed tokens accepted prefix emitted one process, one set of binaries Neutrino-1 0.6B, 328 MB Neutrino-1 8B, 3.88 GB six proposed tokens accepted prefix Weights resident 3.88 GB verifier plus 328 MB draft, one process 4.20 GB Draft surcharge the extra weight bytes the pairing costs 8.46% Shared cache 144 KiB on the 8B, 112 KiB on the draft; 1 GiB at 4k context 256 KiB per token Certified run draft plus verify against plain greedy, zero divergences 27,648 tokens The drafted pair drawn to byte scale, with the residency each side costs.
Drafting on a laptop
The pairing is not a datacenter feature. On a 16 GB Apple M5 both models load into one MLX process under a 6 GiB cap and peak at 4.3 GiB together, with the draft accounting for 0.53 GiB of it. The exactness gate returns 6 of 6 prompts token-identical with drafting on and off, and on factual prompts the drafted rate is 25.71 tok/s against 22.00 plain at an acceptance of 0.744.