Qwen3.5 0.8B is Alibaba's language model. Alibaba's smallest Qwen3.5 model at 0.8B parameters, featuring a hybrid Gated Delta Networks and sparse MoE architecture with a 262K token context window.
Specifications
Canonical IDalibaba-qwen3-5-0-8b
TypeLanguage
StatusActive
CreatorAlibabaAlibaba
Input ModalitiesText
Output ModalitiesText
Parameters0.8B
Benchmarks
Intelligence Index
5.0
#391
Coding Index
15.0
#70
GPQA
0.1
#462
HLE
0.0
#459
IFBench
0.2
#388
Time to First Token
0.47s
#242
SciCode
0.0
#455
LCR
0.1
#324
TerminalBench Hard
0.0
#347
TAU2
0.5
#177
Output TPS
41.1
#248

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
EAGLE Qwen 2.5 3B InstructAvailable
Qwen3.7 Plus1.0M$0.320$1.28Available
Qwen3.7 Max1.0M$1.25$3.75Available
Qwen3.6 Max Preview262K$1.04$6.24Available
Qwen3.6 27B262K$0.150$0.500Available
Qwen3.6 35B A3B262K$0.140$0.450Available
Qwen3.6 Plus1.0M$0.325$1.95Available
Qwen3 Max Thinking262K$0.780$3.90Available
Qwen3 Next 80B A3B128K$0.140$1.20Available
Qwen3 Max262K$0.359$1.43Available
Qwen3.5 0.8BCurrent

Model IDs

alibaba-qwen3-5-0-8b
huggingface-vlm-qwen3-5-0-8b
Qwen/Qwen3.5-0.8B
qwen3-5-0-8b
qwen3-5-0-8b-non-reasoning