> 260k context
with a single 5090?
Yep, Gated DeltaNet in Qwen3.6 requires much less VRAM for the KV cache than previous generations. Plus the KV cache is 8-bit.
is it in llama.cpp?
Yep, Gated DeltaNet in Qwen3.6 requires much less VRAM for the KV cache than previous generations. Plus the KV cache is 8-bit.
is it in llama.cpp?