Model Releases
One GPU, 1M context, Day-0 ready. Big props to the vLLM team for the seamless integration!π Try Qwen3.8-27B on vLLM: @vllm_project https://β¦
One GPU, 1M context, Day-0 ready. Big props to the vLLM team for the seamless integration!π Try Qwen3.8-27B on vLLM: @vllm_project https://recipes.vllm.ai/Qwen/Qwen3.8-27B π Qwen3.8-27B is here from @
One GPU, 1M context, Day-0 ready. Big props to the vLLM team for the seamless integration!π Try Qwen3.8-27B on vLLM: @vllm_project https://recipes.vllm.ai/Qwen/Qwen3.8-27B π Qwen3.8-27B is here from @Alibaba_Qwen, and the whole thing fits on a single GPU. Same hybrid backbone as the 2.4T flagship, dense instead of MoE. Day-0 support in vLLM. π What is in it for serving β¨ - Fits one Blackwell GPU in every precision. Qwen ships BF16 and FP8, the NVβ¦
Related
- Less than 2 hours to say hiπ. It's almost time! See you soon: π https://huggingface.co/Qwen/Qwen3.8-27B
- Day 0 vLLM support for Qwen3.6-27B! @vllm_project β₯οΈβ€οΈ
- Qwen3.8-27B is available on @ollama οΌAny harness you run, the model always delivers. Let's code together, and show us what you build.π
Source: Qwen (X) | 2026-08-14