What are the hardware requirements for Zephyr 220M Sft Full?

Zephyr 220M Sft Full 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 Zephyr 220M Sft Full and how large is it?

Zephyr 220M Sft Full 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 Zephyr 220M Sft Full perform on standard benchmarks?

Zephyr 220M Sft Full has the following published scores: MMLU 26.45. Compare against reference models on this page or on the LLM Explorer leaderboards.

Zephyr 220M Sft Full by BEE-spoke-data — VRAM 0.4GB, 2K context

Name: Zephyr 220M Sft Full
Author: BEE-spoke-data

Zephyr 220M Sft Full is an open-source language model by BEE-spoke-data. Features: 220m LLM, VRAM: 0.4GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.15, Arc: 25.3, HellaSwag: 29, MMLU: 26.5, GSM8K: 0.4.

Base model:bee-spoke-data/smol... Base model:finetune:bee-spoke-... Conversational Dataset:huggingfaceh4/ultracha... Endpoints compatible Generated from trainer Mistral Region:us Safetensors Tensorboard

Model Card on HF 🤗: https://huggingface.co/BEE-spoke-data/zephyr-220m-sft-full

Zephyr 220M Sft Full Parameters and Internals

Training Details

Data Sources:

HuggingFaceH4/ultrachat_200k

LLM Name	Zephyr 220M Sft Full
Repository 🤗	https://huggingface.co/BEE-spoke-data/zephyr-220m-sft-full
Base Model(s)	Smol Llama 220M Openhermes BEE-spoke-data/smol_llama-220M-openhermes
Model Size	220m
Required VRAM	0.4 GB
Updated	2026-08-13
Maintainer	BEE-spoke-data
Model Type	mistral
Model Files	0.4 GB 0.0 GB
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.37.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32128
Torch Data Type	bfloat16

Rank the Zephyr 220M Sft Full 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 Zephyr 220M Sft Full

Best Alternatives	Context / RAM	Downloads	Likes
Zephyr 220M DPO Full	2K / 0.4 GB	9	2