Unsloth 支持 DeepSeek V4 Flash 0731 本地运行
DeepSeek V4 Flash 0731 can now be run locally! 🐳
Unsloth 宣布 DeepSeek V4 Flash 0731 现已可在本地运行，无损 4-bit 量化需 168GB 内存，3-bit 需 110GB 内存，可通过 Unsloth 或 llama.cpp 运行，并提供了指南和 GGUF 链接。Unsloth 称 V4 Flash 0731 表现优于 V4 Pro，更小的量化版本当天晚些时候发布。DeepSeek 官方此前宣布 DeepSeek-V4-Flash 官方 API 进入公开测试，Agent 能力大幅升级，基准分数超过 V4-Pro-Preview，并原生支持 Responses API 格式、适配 Codex。
查看原帖🚀 DeepSeek-V4-Flash Official API is now LIVE in public beta! 🔷 We’ve massively upgraded its Agent capabilities—benchmark scores are now far surpassing the V4-Pro-Preview. Check out the massive performance leap below! 👇 🔷 The official V4-Flash now natively supports the Responses API format and is fully adapted for Codex! Check out the configuration…
展开完整原文
🚀 DeepSeek-V4-Flash Official API is now LIVE in public beta! 🔷 We’ve massively upgraded its Agent capabilities—benchmark scores are now far surpassing the V4-Pro-Preview. Check out the massive performance leap below! 👇 🔷 The official V4-Flash now natively supports the Responses API format and is fully adapted for Codex! Check out the configuration details in our official API docs: https://t.co/smCwQZMeiq
正文
当前显示原文，中文全文译文尚未就绪。
DeepSeek V4 Flash 0731 can now be run locally! 🐳
Run DeepSeek V4 Flash lossless 4-bit on 168GB RAM and 3-bit on 110GB RAM.
V4 Flash 0731 outperforms V4 Pro. Run via Unsloth or llama.cpp. Smaller quants coming today.