Unsloth AI· @UnslothAI · X·· 2 小时前精选AI 评分69
AI 导读
Unsloth 发布 DeepSeek-V4.1-Flash-1017 的 Dynamic V3.1 GGUF 量化版，称其在 GPQA Diamond、AIME25、LiveCodeBench v6、MMLU-Pro、Aider 等基准上领先同类量化版本。模型需 64GB 以上内存运行，GGUF 已上传 Hugging Face，并附部署博客。
推荐理由
Unsloth 发布了 DeepSeek-V4.1-Flash-1017 的 Dynamic V3.1 GGUF 量化版，并给出多项基准对比和显存需求，方便本地部署选型。
正文 · 原文
We’re releasing new DeepSeek-V4.1-Flash-1017 GGUFs, ranking highest across benchmarks.
Dynamic V3.1 leads across nearly all benchmarks: GPQA Diamond, AIME25, LiveCodeBench v6, MMLU-Pro, Aider & more.
Run on 64GB+ RAM.
GGUF: https://huggingface.co/unsloth/DeepSeek-V4.1-Flash-1017-GGUF
Blog: https://unsloth.ai/docs/models/deepseek-v4.1-flash
🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API. 🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model. 1/4在 X 查看被引用的帖子
来源：Unsloth AI · x.com