Qwen3.5-0.8B

Home/Models/Qwen/Qwen3.5-0.8B

Qwen/Qwen3.5-0.8B

kind: original
quant: bf16 (16-bit)
family: qwen
modality: image-text-to-text
root model: Qwen/Qwen3.5-0.8B-Base
provider: Qwen
license: apache-2.0
language: —
context: 262,144
library: transformers
vRAM (GB): —
size on disk: —
downloads: 2,789,363
likes: 643
created: —
last modified: 2026-03-02T11:26:58+00:00 (2026)
huggingface: https://huggingface.co/Qwen/Qwen3.5-0.8B
tags: transformerssafetensorsqwen3_5image-text-to-textconversationalbase_model:Qwen/Qwen3.5-0.8B-Basebase_model:finetune:Qwen/Qwen3.5-0.8B-Baselicense:apache-2.0eval-resultsendpoints_compatibledeploy:azureregion:usdeploy:sagemaker

no scores extracted for this variant.

title	author	status	type
Add IFStruct v1.0 evaluation result	SaylorTwift	open	disc
Listed on OpenModelMap	duola15	open	disc
aaaa	Aniskhan29	draft	disc
Add EvalEval community eval results	EvalEvalBot	closed	disc
Add MMMU-Pro evaluation result	SaylorTwift	open	disc
Add ParseBench evaluation results	boyang-runllama	open	disc
0.8B with mtp is slower than without mtp	WEISHU	open	disc
fix chat template to avoid empty historical `<think>` blocks	latent-variable	open	disc
When vllm deployment is started using mtp config, an error will be reported. Please help！	WEISHU	open	disc
anis	Aniskhan29	draft	disc
Add ScreenSpot-Pro evaluation result	merve	open	disc
my frist pull	liponnif	closed	disc
How to change the model to ONNX format	WangJH97	open	disc
Can I run this on the macbook apple Silicon?	anuedaraanu	open	disc
Request format for transformers serve for Qwen3.5	Crockrocks12	open	disc
Is there a comparison between Qwen3.5-0.8B and Qwen3-0.6B?	sssssp	open	disc
Can I run these models on google collab ? Please Help!!	saikumar305	open	disc
Could someone make Qwen/Qwen3.5-0.4B?	MihaiPopa-1	open	disc
Will there be embedding only versions of these models?	vincevannnoort	open	disc
Installation Video and Testing - Step by Step	fahdmirzac	open	disc
Add MMLU-Pro evaluation result	SaylorTwift	open	disc