Unsloth 发布 DeepSeek V4.1-Flash-1017 1-bit GGUF
Unsloth 发布了 DeepSeek V4.1-Flash-1017 的 GGUF 本地部署版本，其中包括 1-bit 构建；公司称该版本保留约 88.2% 的准确率，并将模型大小从 508GB 降至 250GB。公司还宣称其基准测试排名领先，但报告未提供独立测量结果，而且不同帖子给出的运行内存要求在 64GB 和 128GB 之间不一致。
这一发布让 DeepSeek V4.1-Flash-1017 能以小得多的格式在本地部署，但准确率、基准表现和硬件要求仍主要来自厂商自述。
DeepSeek V4.1-Flash-1017 can now run locally! 🐳 We made 1-bit retain ~88.2% accuracy while shrinking size from 508GB to 250GB (−52%). Run on a 128GB+ RAM device. V4.1 Flash 1017 is the strongest open model to date Guide: https://unsloth.ai/docs/models/deepseek-v4.1-flash GGUF: https://huggingface.co/unsloth/DeepSeek-V4.1-Flash-1017-GGUF
DeepSeek: 🚀 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,
#DeepSeek V4.1-Flash-1017#Unsloth#DeepSeek#Dynamic V3.1#DeepSeek Harness#Tencent CodeBuddy