FoxlightAI/qwen3-8-27b-obliterated-mtp

This repository contains an MTP speculative-decoding sidecar derived from OBLITERATUS/Qwen3.8-27B-OBLITERATED. It is not a standalone model โ€” it provides the multi-token-prediction heads used by Skulk to speculatively decode for the target model OBLITERATUS/Qwen3.8-27B-OBLITERATED. 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 OBLITERATUS/Qwen3.8-27B-OBLITERATED
Source revision 08a7ab67298e9ffab4b55612d946cc96e1e34c6f
Target model OBLITERATUS/Qwen3.8-27B-OBLITERATED
Extracted with skulk-weights-publisher 0.1.0
Generated 2026-08-21T17:17:57Z

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 OBLITERATUS/Qwen3.8-27B-OBLITERATED 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/qwen3-8-27b-obliterated-mtp

Base model

Qwen/Qwen3.8-27B
Finetuned
(1)
this model

Collection including FoxlightAI/qwen3-8-27b-obliterated-mtp