What are the hardware requirements for Smol Llama 101M Chat V1?

Smol Llama 101M Chat V1 requires approximately 0.4 GB of VRAM and supports a context window of 1K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Smol Llama 101M Chat V1 and how large is it?

Smol Llama 101M Chat V1 is developed by Felladrin, a model with 101m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Smol Llama 101M Chat V1 perform on standard benchmarks?

Smol Llama 101M Chat V1 has the following published scores: MMLU 24.93. Compare against reference models on this page or on the LLM Explorer leaderboards.

Smol Llama 101M Chat V1 by Felladrin — VRAM 0.4GB, 1K context

Name: Smol Llama 101M Chat V1
Author: Felladrin

Smol Llama 101M Chat V1 is an open-source language model by Felladrin. Features: 101m LLM, VRAM: 0.4GB, Context: 1K, License: apache-2.0, LLM Explorer Score: 0.15, Arc: 22.9, HellaSwag: 28.7, MMLU: 24.9, GSM8K: 0.1.

Base model:bee-spoke-data/smol... Base model:finetune:bee-spoke-... Conversational Dataset:cognitivecomputations/... Dataset:ldjnr/capybara Dataset:open-orca/slimorca-ded... Dataset:starfishmedical/webgpt... Dataset:thudm/webglm-qa Dataset:vmware/open-instruct En Endpoints compatible Llama Model-index Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/Felladrin/Smol-Llama-101M-Chat-v1

Smol Llama 101M Chat V1 Parameters and Internals

Model Type

text generation, chat

Additional Notes

Multiple format availability: GGUF, ONNX, MLC.

LLM Name	Smol Llama 101M Chat V1
Repository 🤗	https://huggingface.co/Felladrin/Smol-Llama-101M-Chat-v1
Base Model(s)	Smol Llama 101M GQA BEE-spoke-data/smol_llama-101M-GQA
Model Size	101m
Required VRAM	0.4 GB
Updated	2026-08-08
Maintainer	Felladrin
Model Type	llama
Model Files	0.4 GB
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	1024
Model Max Length	1024
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32128
Torch Data Type	float32

Rank the Smol Llama 101M Chat V1 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 Smol Llama 101M Chat V1

Best Alternatives	Context / RAM	Downloads	Likes
Smol Llama 101M GQA	1K / 0.4 GB	465	33
...ephyr Smol Llama 100M Sft Full	1K / 0.2 GB	97	1
...Llama 101M Midjourney Messages	1K / 0.4 GB	13	1
Smol Llama 101M GQA Python	1K / 0.4 GB	14	1

Note: green Score (e.g. "73.2") means that the model is better than Felladrin/Smol-Llama-101M-Chat-v1.