What are the hardware requirements for SmolLM2 360M?

SmolLM2 360M requires approximately 0.7 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed SmolLM2 360M and how large is it?

SmolLM2 360M is developed by HuggingFaceTB, a model with 360m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate SmolLM2 360M?

SmolLM2 360M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

SmolLM2 360M by HuggingFaceTB — VRAM 0.7GB, 8K context

Name: SmolLM2 360M
Author: HuggingFaceTB

SmolLM2 360M is an open-source language model by HuggingFaceTB. Features: 360m LLM, VRAM: 0.7GB, Context: 8K, License: apache-2.0, LLM Explorer Score: 0.24.

Arxiv:2502.02737 Deploy:azure En Endpoints compatible Eval-results Llama Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/HuggingFaceTB/SmolLM2-360M

SmolLM2 360M Parameters and Internals

Model Type

language model, instruction model

Use Cases

Primary Use Cases:

text rewriting, summarization, function calling

Limitations:

Primarily understands and generates content in English, Generated content may not be factually accurate or logically consistent, Bias may be present in the training data

Considerations:

Use as assistive tools, always verify critical information

Supported Languages

en (High proficiency)

Training Details

Data Sources:

FineWeb-Edu, DCLM, The Stack

Data Volume:

4 trillion tokens

Methodology:

Supervised fine-tuning and Direct Preference Optimization (DPO)

Hardware Used:

64 H100 GPUs

Model Architecture:

Transformer decoder

Input Output

Accepted Modalities:

text

LLM Name	SmolLM2 360M
Repository 🤗	https://huggingface.co/HuggingFaceTB/SmolLM2-360M
Model Size	360m
Required VRAM	0.7 GB
Updated	2026-07-19
Maintainer	HuggingFaceTB
Model Type	llama
Model Files	0.7 GB
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.40.1
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	49152
Torch Data Type	bfloat16

Rank the SmolLM2 360M capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to SmolLM2 360M

Best Alternatives	Context / RAM	Downloads	Likes
Smol Lm2 360 Instruct	8K / 0.7 GB	313	3
SmolLM2 360M Instruct	8K / 0.7 GB	476032	208
Smollm2 360M Text2sql Sft	8K / 1.4 GB	194	0
Nuevamol 360M Init	8K / 0.7 GB	21	0
Nuevamol 360M 6Btok Wd5	8K / 0.6 GB	6	0
Smollm3 720prms	8K / 0.7 GB	5	0
Auto Completer 0.1	8K / 1.4 GB	7	1
ProseFlow V1 360M Instruct	8K / 0.7 GB	5	1
TwinSmolLM2 360M	8K / 0.7 GB	5	0
YarnGPT2	8K / 0.7 GB	3431	6

Note: green Score (e.g. "73.2") means that the model is better than HuggingFaceTB/SmolLM2-360M.