🤯 炸裂！Qwen 3.0-8B从BF16 → 12位完全无损压缩居然成功了！打脸压缩一定有损的言论！

This is a AI post classified by AGK Intelligence as AI infra & evals (a tool drop), kept by the AI Radar because it carries real work, not commentary.

🤯 炸裂！Qwen 3.0-8B从BF16 → 12位完全无损压缩居然成功了！打脸压缩一定有损的言论！ @AlpinDale 基于 Together AI 的 NyoomFloat12，已中 NeurIPS 2026 实现： 🔹99.7%权重指数高4位全是0111，直接砍掉不存，解码时瞬间还原 🔹仅0.3%异常值用escape buffer精确保存，比特级无损 🔹解码后与原BF16逐比特一致，输出结果完全相同 🔹实测内存：Qwen3-8B省21%（3.2GiB），30B-A3B省24.4%（13.88GiB） 🔹吞吐提升最高​+17.8%，还省带宽，速度反而更快 🔹vLLM已有PR支持在线量化，直接可用 以前觉得“压缩就一定有损”，现在被彻底打脸。 无损还能加速，这才是真正的降维打击。 #NyoomFloat12 #NF12 #Qwen #LLM #AI推理加速 #NeurIPS2026 #无损压缩 #vLLM #阿里巴巴

Posted by SuSu_酥酥👅 (27.1k followers) 8 h ago · 30 likes · 3.4k views · view the original post on X. Kept by the AI Radar as AI infra & evals. Tools mentioned: nf12.

More AI work like this

• The enterprise AI bottleneck has moved from models and GPUs to the data path. — @Dell
• AMD Localmaxxers are getting serious about inferencing. 🤯 — @TeksEdge
• We evaluated Nexus on 7 benchmarks and 1,222 tasks. It defines the Pareto frontier. — @FireworksAI_HQ
• There is a 560B model running with its full 1M context on 2x DGX Sparks by @andersjw_. — @plotarmordev
• 免费GPT的API，手快有手慢无 — @mylifcc
• TensorFold 1.2.4 is out. 🚀 — @ashxhart
• AWS is making it easier to run several smaller models on the same GPU. — @markfenner
• The @nvidia Jetson Orin Nano is back in the lab. — @jmurillocode

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.2k posts from 5k X accounts over the last 14 days, 10.5k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-07 16:40 UTC. Full method.