Try Ling-3.0-flash locally on different devices! Thanks @atomic_chat_hq for the day0 community support! 🥰 Any questions or issues, please come to our Discord channel https://discord.gg/jQtDsU5J6C to discuss~ 🤠
AI 导读
蚂蚁百灵推出 Ling-3.0-flash 本地部署方案,获 Atomic Chat 社区首日支持。Hugging Face 已发布从无损 BF16 到 1-bit 的 GGUF 量化版本及 NVFP4 格式。其中 AD-Q5_K_M 最适合 128GB 硬件(DGX Spark 测试),token 匹配率达 97.5%,漂移比同尺寸 llama.cpp 默认量化低 31%。
Try Ling-3.0-flash locally on different devices! Thanks @atomic_chat_hq for the day0 community support! 🥰 Any questions or issues, please come to our Discord channel https://discord.gg/jQtDsU5J6C to discuss~ 🤠
Run Ling 3.0 Flash locally 🌀 We released GGUF quants on Hugging Face, from lossless BF16 to 1-bit, plus NVFP4! AD-Q5_K_M is the best fit for 128GB hardware (te...
来源:Ant Ling· x.com