New models are pushing context windows toward one million tokens, but key-value caches make VRAM a critical bottleneck. The trend highlights the gap between long-context capabilities and self-hosted feasibility.
The pull request in qwen-code signals that Qwen4 targets a one-million-token window. For self-hosted inference the cost is not theoretical: the key-value cache grows with tokens and fills VRAM along with weights. Qwen4-27B makes multi-GPU setups or a...
Alibaba brings Qwen4 to a one-million-token context window. The news emerges from a pull request in qwen-code: Qwen4-27B is expected tomorrow at the Apsara event in the Netherlands, while Qwen4-max is dated November 1st with October 1st as a likely p...
The Ling-3.1-flash-1019 checkpoint is now on Hugging Face along with a BF16 base model for custom post-training. Total parameters remain 560B with 25B active and a 1M token context window. Reported scores move from 41 to 44 on AA Intelligence Index v...
inclusionAI updates Ling-3.1-flash: 560B total parameters, 25B active per token, and a 1M token context window. Agentic and scientific benchmarks improve. The base checkpoint is opened for research. The article analyzes implications for self-hosting ...
