What are the hardware requirements for SmolLM3 3B GSM8K SFT?

SmolLM3 3B GSM8K SFT requires approximately 6.2 GB of VRAM and supports a context window of 64K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed SmolLM3 3B GSM8K SFT and how large is it?

SmolLM3 3B GSM8K SFT is developed by HuggingFaceTB, a model with 3b 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 SmolLM3 3B GSM8K SFT?

SmolLM3 3B GSM8K SFT is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

SmolLM3 3B GSM8K SFT by HuggingFaceTB — VRAM 6.2GB, 64K context

Name: SmolLM3 3B GSM8K SFT
Author: HuggingFaceTB

SmolLM3 3B GSM8K SFT is an open-source language model by HuggingFaceTB. Features: 3b LLM, VRAM: 6.2GB, Context: 64K, License: apache-2.0, LLM Explorer Score: 0.24.

Base model:finetune:huggingfac... Base model:huggingfacetb/smoll... Conversational Dataset:meta-math/metamathqa Deploy:azure En Finetuned Gsm8k Math Model-index Reasoning Region:us Safetensors Sft Sharded Smollm3 Tensorflow

Model Card on HF 🤗: https://huggingface.co/HuggingFaceTB/SmolLM3-3B-GSM8K-SFT

SmolLM3 3B GSM8K SFT Parameters and Internals

LLM Name	SmolLM3 3B GSM8K SFT
Repository 🤗	https://huggingface.co/HuggingFaceTB/SmolLM3-3B-GSM8K-SFT
Base Model(s)	SmolLM3 3B Base HuggingFaceTB/SmolLM3-3B-Base
Model Size	3b
Required VRAM	6.2 GB
Updated	2026-08-09
Maintainer	HuggingFaceTB
Model Type	smollm3
Model Files	5.0 GB: 1-of-2 1.2 GB: 2-of-2 0.0 GB
Supported Languages	en
Model Architecture	SmolLM3ForCausalLM
License	apache-2.0
Context Length	65536
Model Max Length	65536
Transformers Version	4.57.6
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|end_of_text\|>
Vocabulary Size	128256

Rank the SmolLM3 3B GSM8K SFT 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 SmolLM3 3B GSM8K SFT

Best Alternatives	Context / RAM	Downloads	Likes
SmolLM3 3B 128K	128K / 6.2 GB	14	1
SmolLM3 3B	64K / 6.2 GB	853423	987
...able SmolLM3 3B Claude Fable 5	64K / 6.1 GB	147	3
SmolLM3 3B Base	64K / 6.2 GB	158973	167
DANTE Mosaic 3.5B	64K / 6.2 GB	115	0
Smollm3 3B Mlx	64K / 2.2 GB	22	0
SmolLM3 3B	64K / 6.2 GB	1547	9
SmolLM3 3B ONNX	64K / GB	175	27
EMOTRON 3B	64K / 6.2 GB	55	1
SmolLM3 3B Base	64K / 6.2 GB	131	5

Note: green Score (e.g. "73.2") means that the model is better than HuggingFaceTB/SmolLM3-3B-GSM8K-SFT.