Qwen3-VL-32B-Instruct

Home/Models/Qwen/Qwen3-VL-32B-Instruct

Qwen/Qwen3-VL-32B-Instruct

kind: original
quant: bf16 (16-bit)
family: qwen
modality: image-text-to-text
root model: Qwen/Qwen3-VL-32B-Instruct
provider: Qwen
license: apache-2.0
language: —
context: ,
library: transformers
vRAM (GB): —
size on disk: —
downloads: 2,929,552
likes: 217
created: —
last modified: 2025-10-21T18:26:34+00:00 (2025)
huggingface: https://huggingface.co/Qwen/Qwen3-VL-32B-Instruct
tags: transformerssafetensorsqwen3_vlimage-text-to-textconversationalarxiv:2505.09388arxiv:2502.13923arxiv:2409.12191arxiv:2308.12966license:apache-2.0endpoints_compatibledeploy:azureregion:us

no scores extracted for this variant.

title	author	status	type
Listed on OpenModelMap	duola15	open	disc
Listed on OpenModelMap	duola15	open	disc
Listed on OpenModelMap	duola15	open	disc
Listed on OpenModelMap	duola15	open	disc
Update config.json	PeterWWWWWW	closed	disc
Configuration issue with tie_word_embeddings when using trl GRPOTrainer with vLLM	DimensionSTP	open	disc
new predict	tangyu12143	draft	disc
Best non-thinking model qwen ever released	BigBlueWhale	open	disc
AWQ version	cormak	open	disc
Recommended model parameters	BigBlueWhale	open	disc
GGUFs have buggy Japanese OCR performance	TPH441	open	disc
'Qwen3VLConfig' object has no attribute 'vocab_size'	vladciocan88	open	disc
How to stop this model from thinking.	CreeperMZ	closed	disc
How about running by llama.cpp	rosspanda0	open	disc