Inference EngineeringAcademy
HomeFoundations Free
Courses
Pricing
Resources
JobsCoding practiceStart learning

Qwen3.5-4B-Base

CheckpointQwen/Qwen3.5-4B-BaseModel card indexedModel card

Support summary

Qwen3.5-4B-Base is a checkpoint published by Qwen, built on the Qwen3_5ForConditionalGeneration architecture. vLLM lists its architecture, but not this exact checkpoint.

Configured context
262,144 tokens
License
apache-2.0
Hugging Face model card
Publisher
Qwen
Task
image text to text
License
apache-2.0
Library
transformers
Architecture
Qwen3_5ForConditionalGeneration
Weight tensor elements
4.7B
Tensor types
BF16, F32
Configured context
262,144 tokens
Weight access
Public
Repository created
2026-02-27
Source 1: Qwen/Qwen3.5-4B-Base · publisher model cardSource 2: Qwen/Qwen3.5-4B-Base · Hugging Face metadataSource 3: Qwen/Qwen3.5-4B-Base · publisher configurationReviewed
Model notes and sources

Engine support

3 engines

Engine support for Qwen3.5-4B-Base
EngineReleaseCheckpoint supportEvidence scopeLast known supported
vLLM0.28.0Newest indexedArchitecture listed; exact checkpoint unknownNo supported release indexed
Features, dependencies and evidence for vLLM 0.28.0
SGLang0.5.19Newest indexedNo matching evidence curatedNo supported release indexed
Features, dependencies and evidence for SGLang 0.5.19
TensorRT-LLM1.2.1Newest indexedNo matching evidence curatedNo supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1