JustFit 让 27B 模型在 24GB 笔记本上处理 20万token

JustFit: 200K-Token LLM Serving on a 24 GiB Laptop with Just-in-Time State Management

Capable open-weight models make local coding and reasoning attractive, but their context and execution state strain laptop memory. We present JustFit, an MLX-based inference runtime that combines KVExec for compressed KV execution, PhaseSwap for component residency, and StateTrans for state-preserving serving transitions. These mechanisms fuse reconstruction and coordinate just-in-time materialization and release, independently of model-weight quantization. In full-execution capacity tests on a 24 GiB M4 Pro MacBook running Qwen3.8-27B MXFP4, three independent runs complete 196,608 input and 16,384 output tokens, increasing completed single-request context from the mlx-vlm baseline's 30,720 positions to 212,992 (6.93x); a separate two-request run retains 229,376 positions in aggregate. In separate performance tests, a 32K-input, 64-output probe reaches 19.11 tokens/s, and a repeated 32K+6K workload has a median peak process footprint of 16,374 MiB. The integrated runtime answers 29 of 30 AIME 2026 problems correctly, showing how compact state and lifetime-aware execution expand local serving capacity while supporting extended generated reasoning.

本条情报归属 AITOP「技巧」核心栏目，重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」「中美大模型技术代差与商业化对照」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：JustFit、Qwen3.8-27B、提示词工程、推理模型，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明：本文原始线索采编自「arXiv cs.AI」（@Yuhua Chen），经 AITOP 多维评分管线结构化提炼。截至目前，全网已有 2 家独立信源对该事件进行交叉印证与跟进报道（含 IT之家 等），属于近期高关注度行业信号。