Qwen3.8 runs on single RTX 4090

Alex Getman @alexgetmancom · 14 Aug 2026, 18:14 UTC · Updated 31 Oct 2026, 22:26 UTC

⚡️ Alibaba released Qwen3.8’s weights

A model at Claude Opus 4.6 level, a flagship just six months ago, can now run on a single RTX 4090. Qwen3.8 27B uses around 17 GB of VRAM when quantized and should deliver ~50 tok/s.

Table comparing performance of models Qwen3.8-27B, Qwen3.6-27B, Qwen3.7-Plus, Muse Glimmer-30B, and Opus4.6 Max across Coding, Agent, and General categories with scores on various benchmarks.

Claude Alibaba Qwen

Русская версия Markdown

17 Sep🚨 Qwen3.8 Omni Flash is out It can see, hear and understand video, then actually act on it Give it hours of footage and it can find the right moments, translate, edit or turn it into notes. Give it a meeting and it can pull out tasks and start working on them 1M context, API…

Alibaba Qwen

26 Aug🚨 QWEN3.8 FLASH NEXT IS OUT The leaked specs were real: • 125B multimodal MoE • Only 6B active • 262K native context, up to 1M Qwen says it beats Claude Opus 4.6 across coding, agentic tasks, tool use and several multimodal benchmarks.

Claude Alibaba Qwen

26 Aug🚨 QWEN3.8 FLASH NEXT DROPS TODAY A ModelScope description that was quickly taken down reportedly revealed: • 125B main parameters • 51B N gram embeddings • Only 6B active per token • Multimodal MoE architecture The model is also an official preview of the upcoming Qwen4…

Alibaba Qwen

18 Aug⚡️ Qwen 3.8 27B beat GPT 5.6 Terra This happened in the AA Agentic Index, a benchmark that tests how well models handle agentic tasks. And you can run Qwen 3.8 27B locally on a single RTX 3090.

Alibaba Qwen

Alibaba released Qwen3.8’s weights

Related posts