Qwen3.5-122B-A10B MoE GPTQ Int4 quantized variant published on Hugging Face
Qwen published a GPTQ 4-bit quantized version of the Qwen3.5-122B-A10B MoE model on Hugging Face. Pipeline tag is image-text-to-text, library is transformers, licensed Apache 2.0.
PUBLISHED2026-03-03
OBSERVED2026-08-11
AGE5mo
SOURCES1
- Model:
Qwen/Qwen3.5-122B-A10B-GPTQ-Int4 - Pipeline: image-text-to-text
- Library: transformers
- License: Apache 2.0
- Tags: qwen3_5_moe, 4-bit, gptq, endpoints_compatible, region:us, deploy:azure
- Repository created: 2026-03-03
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.