News for hackers. Stuff that matters.

A comment on Qwen3.5: Towards Native Multimodal Agents. Parent comment

Re:Qwen3.5: Towards Native Multimodal Agents by alex43578 on Tuesday February 17, 2026 @02:03AM (#47044536)
NVIDIA is showing training at 4 bits (NVPF4), and 4 bit quants have been standard for running LLMs at home for quite a while because performance was good enough.
[ Parent | on HN ]

There are no comments on this comment yet.