397b - Robuta Search

https://simonwillison.net/2026/Mar/18/llm-in-a-flash/ Autoresearching Apple's "LLM in a Flash" to run Qwen 397B locally Here's a fascinating piece of research by Dan Woods, who managed to get a custom version of Qwen3.5-397B-A17B running at 5.5+ tokens/second on a 48GB MacBook... apple llm flash run qwen https://huggingface.co/Qwen/Qwen3.5-397B-A17B?inference_api=true&inference_provider=scaleway Qwen/Qwen3.5-397B-A17B · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. qwen qwen3 5 397b a17b hugging face https://automatio.ai/models/qwen3-5-397b-a17b Qwen3.5-397B-A17B: 1M Context & Native Multimodal Reasoning Qwen3.5-397B-A17B is Alibaba's flagship open-weight MoE model. It features native multimodal reasoning, a 1M context window, and a 19x decoding throughput... qwen3 5 397b 1m context native multimodal a17b reasoning https://huggingface.co/Qwen/Qwen3.5-397B-A17B Qwen/Qwen3.5-397B-A17B · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. qwen qwen3 5 397b a17b hugging face https://welinux.com/topic/20/qwen-发布-27b-稠密开源模型-编程能力超越旧旗舰-397b-moe-模型/1 Qwen 发布 27B 稠密开源模型，编程能力超越旧旗舰 397B MoE 模型 | WeLinux Qwen 团队于 2026 年 4 月 22 日正式发布 Qwen3.6-27B，现已上线 Hugging Face 和 ModelScope。该模型声称在所有主要编程基准测试中，超越了上一代开源旗舰模型 Qwen3.5-397B-A17B（总参数 397B，激活参数 17B 的 MoE 架构）。值得注意的是，... qwen 27b 397b moe welinux https://huggingface.co/Qwen/Qwen3.5-397B-A17B?inference_api=true&inference_provider=together Qwen/Qwen3.5-397B-A17B · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. qwen qwen3 5 397b a17b hugging face https://huggingface.co/Qwen/Qwen3.5-397B-A17B/blob/main/model.safetensors-00014-of-00094.safetensors model.safetensors-00014-of-00094.safetensors · Qwen/Qwen3.5-397B-A17B at main We’re on a journey to advance and democratize artificial intelligence through open source and open science. qwen qwen3 5 397b a17b model safetensors 00014 https://huggingface.co/Qwen/Qwen3.5-397B-A17B/commit/556af785fedb4908b43648afdc0fb5a19138edf7 Add files using upload-large-folder tool · Qwen/Qwen3.5-397B-A17B at 556af78 We’re on a journey to advance and democratize artificial intelligence through open source and open science. qwen qwen3 5 add files upload large 397b a17b using https://huggingface.co/Qwen/Qwen3.5-397B-A17B/tree/main Qwen/Qwen3.5-397B-A17B at main We’re on a journey to advance and democratize artificial intelligence through open source and open science. qwen qwen3 5 397b a17b main https://www.kuwanb.com/post-7473.html gitcode免费提供不限 Token 用量Qwen3.5-397B-A17B大模型-酷玩资源网 - 免费资源下载_每日更新资源网站_kuwanb.com 先申明，不是推广，有需要的自取gitcode免费提供不限Token用量Qwen3.5-397B-A17B大模型，需每24小时领取一次1、登录网站：https://ai.gitcode.com/serv... 5 397b token kuwanb https://huggingface.co/Qwen/Qwen3.5-397B-A17B/blob/main/model.safetensors-00010-of-00094.safetensors model.safetensors-00010-of-00094.safetensors · Qwen/Qwen3.5-397B-A17B at main We’re on a journey to advance and democratize artificial intelligence through open source and open science. qwen qwen3 5 397b a17b model safetensors 00010 https://nowokay.hatenablog.com/entry/2026/02/24/161402 Qwen3.5-397B-A17Bのコーディングを試す。型の扱いは苦手だけど安定感がある - きしだのHatena Feb 24, 2026 - Qwen3.5-397B-A17BのUnsloth版Q4_K_MをMac Studio 512GBで試しています。今回はコーディングについて。一般性能はこちら。 Qwen3.5-397B-A17Bを試す。日本知識が細かくOCR性能も高く実用的～一般性能編～ - きしだのHatena... qwen3 5 397b