--- base_model: Qwen/Qwen3-Next-80B-A3B-Thinking tags: - mtp-sidecar - skulk - foxlight license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking/blob/main/LICENSE foxlight: artifact_type: mtp-sidecar source_repo: Qwen/Qwen3-Next-80B-A3B-Thinking source_revision: e502dd4100cc68c0de57643fd4317ec93a128670 target_model: Qwen/Qwen3-Next-80B-A3B-Thinking extracted_with: skulk-weights-publisher 0.1.0 generated_at: '2026-06-03T00:38:08Z' --- # FoxlightAI/qwen3-next-80b-a3b-thinking-mtp This repository contains an **MTP speculative-decoding sidecar** derived from [`Qwen/Qwen3-Next-80B-A3B-Thinking`](https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking). It is **not a standalone model** — it provides the multi-token-prediction heads used by [Skulk](https://github.com/Foxlight-Foundation/Skulk) to speculatively decode for the target model **`Qwen/Qwen3-Next-80B-A3B-Thinking`**. The heads ship at full precision (**bf16, unquantized**) — they are the speculative drafter, where precision drives draft acceptance — 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-Next-80B-A3B-Thinking` | | Source revision | `e502dd4100cc68c0de57643fd4317ec93a128670` | | Target model | `Qwen/Qwen3-Next-80B-A3B-Thinking` | | Extracted with | skulk-weights-publisher `0.1.0` | | Generated | 2026-06-03T00:38:08Z | ## 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-Next-80B-A3B-Thinking`](https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking) 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.