qwen3.8-flash-next
qwen3.8-flash-next is Image-Text-to-Text model with 180B parameters. Download, explore files and run it on Hugging Face.. It is ranked #3259 on the AI Radar, in Open & local models, first seen 55 days ago and shared in 3 posts (60.9k views).
Qwen/Qwen3.8-Flash-Next · Hugging Face Hugging Face Log In Sign Up <|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%-…
What people said about qwen3.8-flash-next on X
🤯我靠！NVIDIA 直接把 Qwen3.8-Flash-Next 砍到原来的 37% 体积！这是 Blackwell 时代真正能跑起来的实用级效率！ 125B MoE + 6B 激活 + 混合注意力（GDN+QSA）+ 51B N-gram Embedding，原版 BF16 约 360GB，NVFP4 版约 2.7x 更小，精度几乎没掉。 关键亮点： 🔹比 Claude Opus 4.6 Max 在 SWE-bench Pro、CoWorkBench、JobBench 等真实任务上更好 🔹原生 262K 上下文，可扩展到 1M 🔹支持文本/图像/视频多模态 🔹路由专家 NVFP4 + 关键层 BF16/FP8…
— @NFT_Chen, 9 days ago · 185 likes · see the post
你以为本地只能跑点玩具模型？现在 8GB 显存的老卡能跑 27B，一台 128GB 的 Mini pc 能跑开源前十的模型。 我按所需显存从小到大总结了 10 个，每一档只留最能打的，对号入座就行。分数用 Artificial Analysis 的智能指数（下面简称 AA 分），开源第一目前是 46.3 分，体积写的是量化后的权重文件，实际跑起来还要给上下文留出余量。 1、Ternary Bonsai 2 27B（8GB 显存） 把 Qwen3.8-27B 的主体权重压成 -1、0、+1 三个值，54GB 的模型缩到 5.95GB。官方跑了 14 项基准，保住原版 98% 的分数，同样压到 2 比特的常规量化只剩 84%。要用…
— @Ryrenz, 12 days ago · 8 likes · see the post
Alternatives to qwen3.8-flash-next
- kimi-k3.1-pro — Releasing the model weights of Kimi K3.1 Pro
- unsloth.ai — Guide to running Mistral Large 4 GGUFs locally with Unsloth and llama.cpp.
- niklaslenz.com — Play the world in your browser. Every number, the exact command and the raw output
- qwen3.8-flash-next-gguf — Image-Text-to-Text model with 177B parameters. Download, explore files and run it on Hugging Face.
- project-maya — Plus a round of fixes, UI improvements and community PRs.
- twil-8b — Text Generation model with 9B parameters. Download, explore files and run it on Hugging Face.
qwen3.8-flash-next in numbers
- Rank on the AI Radar: #3259 of 10425
- Shared in 3 posts by 2 accounts: @NFT_Chen, @Ryrenz
- 60.9k views on those posts
- First seen 55 days ago, last shared 9 days ago
- Pricing seen by AGK Intelligence: not stated
- Market: Open & local models
FAQ
What is qwen3.8-flash-next?
Image-Text-to-Text model with 180B parameters. Download, explore files and run it on Hugging Face. It was first shared on X 55 days ago and is ranked #3259 on the AI Radar.
Is qwen3.8-flash-next free?
Pricing is not stated on the page we read.
Who shared qwen3.8-flash-next?
2 accounts on X, including @NFT_Chen, @Ryrenz, in 3 posts totalling 60.9k views.
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. 65.3k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 17:44 UTC. Full method.