商汤为开源模型 SenseNova-Loop-9B 补充了更多运行方式,包括约 4.9 GB 的 4-bit AWQ 版本及配套 MTP 草稿模型,以及 Q4_K_M、Q5_K_M、Q8_0 和 BF16 四种 GGUF 格式,可在其 llama.cpp fork 中使用。两个版本已分别上线 Hugging Face 的 SenseNova-Loop-9B-AWQ 与 SenseNova-Loop-9B-GGUF 仓库。此前发布的该模型为 9B 参数,支持最高 512K 上下文和文本、图像输入。
More ways to run #SenseNova-Loop-9B!
🔹 4-bit AWQ (~4.9 GB), with a matching MTP draft model
🔹 GGUF in Q4_K_M, Q5_K_M, Q8_0 and BF16, for use with our llama.cpp fork
🤗 AWQ: https://huggingface.co/sensenova/SenseNova-Loop-9B-AWQ
🤗 GGUF: https://huggingface.co/sensenova/SenseNova-Loop-9B-GGUF
💬 Give them a try and share your feedback!
【引用 @SenseTime_AI】#SenseNova-Loop-9B is officially here — now #OpenSource!
Just 9B parameters, competitive with Qwen3.8-27B across multiple benchmarks.
🔹 Big gains over Preview: NL2Repo 19.91 → 41.36; AutomationBench 14.33 → 36.67; GAIA 37.86 → 69.90
🔹 Loop + mHC: 32 unique layers, 56 layer executions
🔹 Day-0 4-bit AWQ weights (~4.9GB), with VRAM needs as low as ~9 GiB at 64K context
🔹 Up to 512K context, with text and image inputs
See what a 9B model can build: animated posters, interactive websites and 3D scenes.
💻 GitHub: https://github.com/OpenSenseNova/SenseNova-Loop
🤗 HF: https://huggingface.co/collections/sensenova/sensenova-loop
👾 Discord: https://discord.com/invite/BuTXPHmQub
#SenseNova-Loop-9B is officially here — now #OpenSource! Just 9B parameters, competitive with Qwen3.8-27B across multiple benchmarks. 🔹 Big gains over Preview: NL2Repo 19.91 → 41.36; AutomationBench 14.33 → 36.67; GAIA 37.86 → 69.90 🔹 Loop + mHC: 32 unique layers, 56 layer executions 🔹 Day-0 4-bit AWQ weights (~4.9GB), with VRAM needs as low as ~9 GiB at 64K context 🔹 Up to 512K context, with text and image inputs See what a 9B model can build: animated posters, interactive websites and 3D scenes. 💻 GitHub: https://github.com/OpenSenseNova/SenseNova-Loop 🤗 HF: https://huggingface.co/collections/sensenova/sensenova-loop 👾 Discord: https://discord.com/invite/BuTXPHmQub在 X 查看被引用的帖子
来源:SenseTime · x.com