What the source record tells us
Current dense Qwen for coding, reasoning and image understanding.
Our catalog records a hybrid cache for this model: full-attention cache and recurrent state have different memory behavior. The linked model page exposes the assumptions used by the calculator; a simple “parameters plus context” shortcut can miss that distinction.
What this means in practice
Start with a modest context and a task you can check. Increase context only after checking the exact runtime configuration and observing memory use. A supported context limit is not a promise that the workload fits your machine.
What this briefing does not establish
This briefing interprets the model-card and configuration records already reviewed for the 99Tokens catalog. It does not report a new release date, independently measured benchmark or fresh availability check. Runtime support and the exact file you use still need checking.