What are the hardware requirements for Smol Llama 220M Open Instruct?

Smol Llama 220M Open Instruct requires approximately 0.4 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Smol Llama 220M Open Instruct and how large is it?

Smol Llama 220M Open Instruct is developed by BEE-spoke-data, a model with 220m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Smol Llama 220M Open Instruct perform on standard benchmarks?

Smol Llama 220M Open Instruct has the following published scores: MMLU 26.11. Compare against reference models on this page or on the LLM Explorer leaderboards.

Smol Llama 220M Open Instruct by BEE-spoke-data — VRAM 0.4GB, 2K context

Name: Smol Llama 220M Open Instruct
Author: BEE-spoke-data

Smol Llama 220M Open Instruct is an open-source language model by BEE-spoke-data. Features: 220m LLM, VRAM: 0.4GB, Context: 2K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.15, Arc: 25, HellaSwag: 29.7, MMLU: 26.1.

Base model:bee-spoke-data/smol... Base model:finetune:bee-spoke-... Dataset:vmware/open-instruct Endpoints compatible Instruct Llama Model-index Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/BEE-spoke-data/smol_llama-220M-open_instruct

Smol Llama 220M Open Instruct Parameters and Internals

Model Type

text-generation

Additional Notes

The model inference API parameters are set to sample with low temperature to ensure some variation in generations. Feel free to experiment with parameter settings.

Training Details

Data Sources:

VMware/open-instruct

Input Output

Input Format:

Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

Output Format:

Responses to the instruction.

Performance Tips:

Experiment with inference parameters for improved performance.

LLM Name	Smol Llama 220M Open Instruct
Repository 🤗	https://huggingface.co/BEE-spoke-data/smol_llama-220M-open_instruct
Base Model(s)	Smol Llama 220M GQA BEE-spoke-data/smol_llama-220M-GQA
Model Size	220m
Required VRAM	0.4 GB
Updated	2026-08-13
Maintainer	BEE-spoke-data
Model Type	llama
Instruction-Based	Yes
Model Files	0.4 GB 0.0 GB
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32128
Torch Data Type	bfloat16

Rank the Smol Llama 220M Open Instruct 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 220M Open Instruct

Best Alternatives	Context / RAM	Downloads	Likes
...l Llama 220M GQA 32K Theta Sft	32K / 0.4 GB	6	2