Robuta

Sponsor of the Day: Jerkmate
https://huggingface.co/mradermacher/Qwen3.5-9B-GLM5.1-Distill-v1-i1-GGUF mradermacher/Qwen3.5-9B-GLM5.1-Distill-v1-i1-GGUF · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. qwen3 5 9bhugging facemradermacherglm51 https://huggingface.co/HauhauCS/Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive HauhauCS/Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. hauhaucs qwen3uncensored aggressivehugging face5122b https://huggingface.co/Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. jackrong qwen3 5claude 4 6opus reasoning distilledv2 ggufhugging face 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 5397b a17bhugging 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 397b1m contextnative multimodala17breasoning 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 5397b a17bhugging face https://www.idp-leaderboard.org/models/qwen3-5-9b Qwen3.5-9B Benchmark Results — IDP Leaderboard | IDP Leaderboard Qwen3.5-9B by Alibaba ranks #12 with 76.7% overall on the IDP Leaderboard. Detailed benchmark scores for OCR, table extraction, KIE, and VQA. qwen3 5 9bbenchmark resultsidp leaderboard https://huggingface.co/blog/mlabonne/qwen35 Qwen3.5: Nobody Agrees on Attention Anymore Feb 19, 2026 - A Blog post by Maxime Labonne on Hugging Face qwen3 5nobodyagreesattentionanymore https://huggingface.co/Qwen/Qwen3.5-27B?inference_api=true&inference_provider=novita Qwen/Qwen3.5-27B · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. qwen qwen3 5hugging face27b https://inference.roboflow.com/workflows/blocks/qwen3.5_vl/ Qwen3.5-VL - Roboflow Inference Scalable, on-device computer vision deployment. qwen3 5roboflow inferencevl https://huggingface.co/mradermacher/Qwen3.5-2B-Claude-Opus-4.6-high-resoning-Base-i1-GGUF mradermacher/Qwen3.5-2B-Claude-Opus-4.6-high-resoning-Base-i1-GGUF · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. claude opus 4qwen3 56 highhugging facemradermacher https://unsloth.ai/docs/models/qwen3.5 Qwen3.5 - How to Run Locally | Unsloth Documentation Run the new Qwen3.5 LLMs including Medium: Qwen3.5-35B-A3B, 27B, 122B-A10B, Small: Qwen3.5-0.8B, 2B, 4B, 9B and 397B-A17B on your local device! run locally unslothqwen3 5documentation https://unsloth.ai/docs/models/qwen3.5/fine-tune Qwen3.5 Fine-tuning Guide | Unsloth Documentation Learn how to fine-tune Qwen3.5 LLMs with Unsloth. fine tuning guideqwen3 5unsloth documentation https://huggingface.co/Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. jackrong qwen3 5claude 4 6opus reasoning distilledhugging face27b https://huggingface.co/Qwen/Qwen3.5-27B Qwen/Qwen3.5-27B · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. qwen qwen3 5hugging face27b https://huggingface.co/Jackrong/Qwen3.5-9B-GLM5.1-Distill-v1 Jackrong/Qwen3.5-9B-GLM5.1-Distill-v1 · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. jackrong qwen3 5hugging face9bglm51 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 5397b a17bhugging 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 5397b a17bmodelsafetensors00014 https://huggingface.co/spaces/Qwen/Qwen3.5-Omni-Offline-Demo Qwen3.5 Omni Offline Demo - a Hugging Face Space by Qwen Enter a task description in the text box and optionally upload one file—an image, an audio clip, or a video. The app sends your input to the Qwen3.5 Omni model... qwen3 5 omnihugging face spaceofflinedemo 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 5add filesupload large397b a17busing 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 5397b a17bmain https://simonwillison.net/2026/Feb/17/qwen35/ Qwen3.5: Towards Native Multimodal Agents Alibaba's Qwen just released the first two models in the Qwen 3.5 series - one open weights, one proprietary. Both are multi-modal for vision input. The open... qwen3 5towards nativemultimodal agents https://www.computerworld.com/article/4133100/alibabas-qwen3-5-targets-enterprise-agent-workflows-with-expanded-multimodal-support-2.html Alibaba’s Qwen3.5 targets enterprise agent workflows with expanded multimodal support –... Feb 17, 2026 - The new model claims benchmark improvements and agent capabilities as competition among Chinese AI vendors accelerates. qwen3 5targets enterpriseagent workflowsexpandedmultimodal https://www.alibabacloud.com/blog/qwen3-5-towards-native-multimodal-agents_602894 Qwen3.5: Towards Native Multimodal Agents - Alibaba Cloud Community We are delighted to announce the official release of Qwen3.5, introducing the open-weight of the first model in the Qwen3. alibaba cloud communityqwen3 5towards nativemultimodal agents https://www.xda-developers.com/qwen-3-5-9b-tops-ai-benchmarks-not-how-pick-model/ Qwen3.5-9B tops every AI benchmark right now, but that's not how you should pick a model Mar 12, 2026 - There's a lot more to a model than just benchmarks. qwen3 5 9btops everyai benchmarkrightpick https://www.jetson-ai-lab.com/models/qwen3-5-27b/ Qwen3.5 27B | Jetson AI Lab Alibaba's dense 27 billion parameter language model with native tool calling and MTP speculative decoding qwen3 5 27bjetson ai lab https://huggingface.co/Qwen/Qwen3.5-4B Qwen/Qwen3.5-4B · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. qwen qwen3 5hugging face4b https://huggingface.co/Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. jackrong qwen3 5claude 4 6opus reasoning distilledv2 ggufhugging face https://www.siliconrepublic.com/machines/alibaba-unveils-qwen3-5-with-visual-agentic-abilities Alibaba unveils Qwen3.5 with visual agentic abilities Feb 16, 2026 - Newer AI model launches from Chinese companies attempt to catch up to their US counterparts in the race for AI dominance. alibaba unveilsqwen3 5visual agenticabilities 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 5397b a17bmodelsafetensors00010 https://automatio.ai/models/qwen3-5-omni Qwen3.5-Omni: 256K Context & Real-Time Multimodal AI Qwen3.5-Omni is a natively omnimodal AI by Alibaba Cloud, offering seamless audio-visual reasoning, real-time voice chat, and 256k context for low-latency apps. qwen3 5 omni256k contextreal timemultimodal ai https://deepswapface.ai/qwen-ai-model/ Qwen3.5: Native Multimodal AI with Visual Agents & Image Generation Animate and refine visuals effortlessly with Qwen 3.5, the alibaba qwen breakthrough in qwen image to video and qwen image editing. qwen3 5native multimodalimage generationaivisual https://huggingface.co/Qwen/Qwen3.5-35B-A3B Qwen/Qwen3.5-35B-A3B · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. qwen qwen3 535b a3bhugging face https://huggingface.co/DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. claude 4 6qwen3 5hugging face40bopus https://aigazine.com/llms/qwen35omni-challenges-gemini-across-100m-hours-of-ai-training-data--s Qwen3.5-Omni Challenges Gemini Across 100M+ Hours of AI Training Data Mar 31, 2026 - Qwen3.5-Omni enters the omni-modal AI arena with strong benchmark results across audio, video, and speech tasks - putting direct pressure on Google's Gemini... qwen3 5 omniai training datachallengesgeminiacross 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 https://www.infoworld.com/article/4133096/alibabas-qwen3-5-targets-enterprise-agent-workflows-with-expanded-multimodal-support.html Alibaba’s Qwen3.5 targets enterprise agent workflows with expanded multimodal support | InfoWorld Feb 17, 2026 - The new model claims benchmark improvements and agent capabilities as competition among Chinese AI vendors accelerates. qwen3 5targets enterpriseagent workflowssupport infoworldexpanded https://huggingface.co/HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. qwen3 5 9buncensored aggressivehugging facehauhaucs https://www.alphaxiv.org/overview/2604.15804 Qwen3.5-Omni Technical Report | alphaXiv Alibaba Cloud's Qwen Team developed Qwen3.5-Omni, a large language model scaling to hundreds of billions of parameters that processes and generates across qwen3 5 omnitechnical reportalphaxiv