DeepSeek Watch posted an update
An AI developer says an NVFP4 version of DeepSeek V4.1 Flash 1017 is now available and is 81GB smaller than the official weights.
Why it mattersThe account says quality looks almost identical, a handy claim for local-model builders, though not a comparative test.
Discuss: Would a smaller model file with reportedly similar quality change which open model you run locally, or do you need independent benchmarks first?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.