• fine-tuning — Taking a trained model and training it a bit more on your own examples so it gets better at one specific job.
• mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
• embedding — A list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.
• context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.

You can fine-tune Qwen's new Engram MoE checkpoint on day one with FSDP2, expert and context parallelism, instead of waiting for community trainer support to catch up to the architecture.

• postQwen3.8-Flash API goes live with 262K context and $0.016 cache reads
• postQwen3.8-Flash opens up the Qwen4 architecture at 6B active parameters
• postQwen3.8-27B leads open models on the Image-to-WebDev Arena
• postNVFP4 serving recipes land for Qwen 3.8 27B

• articleExperiment with Qwen3.8-Flash-Next 176B Model on NVIDIA GB300 NVL72 for Agentic CodingMichelle Horton
• postQwen3.8-Flash opens up the Qwen4 architecture at 6B active parametersQwen
• articleDeveloping Nemotron 3.5 Lightning NVFP4 with QAD Using NVIDIA Model OptimizerTanya Lenz

Checking sign-in…

Loading comments…