Skip to content

Published models

What this page covers

This page lists published model families, their lineage, and model-card template mapping. Use it as an index before downloading, publishing, or extending model cards.

When to use

  • You need the right Hugging Face collection link.
  • You want to understand how each model family is derived.
  • You need the correct README template for a given model type.

Collections on Hugging Face Hub

CollectionDescriptionSizes
Qwen3.5 BNB 4-bitVLM, BNB NF4 quantized0.8B · 2B · 4B · 9B
Qwen3.5 TextText-only bf160.8B · 2B · 4B · 9B
Qwen3.5 Text BNB 4-bitText-only BNB NF40.8B · 2B · 4B · 9B
Qwen3.5 Text GGUFText-only GGUF (Q8 to Q4)0.8B · 2B · 4B · 9B

Model lineage

Lineage note:

  • GGUF base_model points to text-only f16 model, because GGUF is a container/quant format change of the text branch.

README templates

FileModel typepipeline_tagbase_model
model_cards/README_Qwen3.5-bnb-4bit.mdBNB 4-bit VLMimage-text-to-textQwen/Qwen3.5-{SIZE}
model_cards/README_Qwen3.5-text.mdf16 text-onlytext-generationQwen/Qwen3.5-{SIZE}
model_cards/README_Qwen3.5-text-bnb-4bit.mdBNB 4-bit text-onlytext-generationtechwithsergiu/Qwen3.5-text-{SIZE}
model_cards/README_Qwen3.5-text-GGUF.mdGGUF quantstext-generationtechwithsergiu/Qwen3.5-text-{SIZE}