FoxlightAI/qwen3-5-27b-mtp

This repository contains an MTP speculative-decoding sidecar derived from Qwen/Qwen3.5-27B. It is not a standalone model โ€” it provides the multi-token-prediction heads used by Skulk to speculatively decode for the target model Qwen/Qwen3.5-27B. The heads ship at full precision (bf16, unquantized) โ€” they are the speculative drafter, where precision drives draft acceptance โ€” so there is one sidecar per base model and it serves every quantization of the target.

Provenance

Field Value
Artifact type mtp-sidecar
Source model Qwen/Qwen3.5-27B
Source revision fc05daec18b0a78c049392ed2e771dde82bdf654
Target model Qwen/Qwen3.5-27B
Extracted with skulk-weights-publisher 0.1.0
Generated 2026-06-02T23:11:34Z

Usage

Skulk loads this sidecar (mtp.safetensors) alongside the target model to enable MTP speculative decoding. It is referenced from the Skulk Weights Publisher catalog and fetched automatically by the Skulk shard downloader; it is not intended to be loaded standalone.

License

This artifact is derived from Qwen/Qwen3.5-27B and is published under that model's original license (apache-2.0), preserved unchanged. Refer to the source model's card for the full terms.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for FoxlightAI/qwen3-5-27b-mtp

Base model

Qwen/Qwen3.5-27B
Finetuned
(298)
this model

Collection including FoxlightAI/qwen3-5-27b-mtp