SmolLM3-3B-ONNX

CheckpointHuggingFaceTB/SmolLM3-3B-ONNXModel card indexedModel card

Support summary

SmolLM3-3B-ONNX is a checkpoint published by Hugging Face, built on the SmolLM3ForCausalLM architecture. vLLM lists its architecture, but not this exact checkpoint.

Configured context
65,536 tokens
License
apache-2.0
Hugging Face model card
Publisher
Hugging Face
Task
text generation
License
apache-2.0
Library
transformers.js
Architecture
SmolLM3ForCausalLM
Configured context
65,536 tokens
Languages
en, fr, es, it, pt, zh, ar, ru
Base models
HuggingFaceTB/SmolLM3-3B
Weight access
Public
Repository created
2025-07-08
Source 1: HuggingFaceTB/SmolLM3-3B-ONNX · publisher model cardSource 2: HuggingFaceTB/SmolLM3-3B-ONNX · Hugging Face metadataSource 3: HuggingFaceTB/SmolLM3-3B-ONNX · publisher configurationReviewed
Model notes and sources

Engine support

3 engines

Engine support for SmolLM3-3B-ONNX
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