release aidev NEEDS REVIEW SIG 1/5

Qwen publishes FP8 quantized Qwen3.5-397B-A17B

Qwen published an FP8 quantized variant of the Qwen3.5-397B-A17B model on Hugging Face. Source confirms it is a quantized version of the full-precision model. No capability or benchmark details are available.

PUBLISHED2026-02-18
OBSERVED2026-08-11
AGE6mo
SOURCES1

Qwen published an FP8 quantized variant of the Qwen3.5-397B-A17B model on Hugging Face. Source confirms it is a quantized version of the full-precision model. No capability or benchmark details are available.

COMMUNITY

No curated reactions recorded for this event. Facts and takes are kept in separate layers — community context is added by hand, never blended into the record above.