What are the hardware requirements for Stablelm 2 Zephyr 1 6B?

Stablelm 2 Zephyr 1 6B requires approximately 1 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Stablelm 2 Zephyr 1 6B and how large is it?

Stablelm 2 Zephyr 1 6B is developed by stabilityai, a model with 6b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Stablelm 2 Zephyr 1 6B perform on standard benchmarks?

Stablelm 2 Zephyr 1 6B has the following published scores: MMLU 42.03. Compare against reference models on this page or on the LLM Explorer leaderboards.

Stablelm 2 Zephyr 1 6B by stabilityai — VRAM 1GB, 4K context

Name: Stablelm 2 Zephyr 1 6B
Author: stabilityai

Stablelm 2 Zephyr 1 6B is an open-source language model by stabilityai. Features: 6b LLM, VRAM: 1GB, Context: 4K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.2, Arc: 43.7, HellaSwag: 69.3, MMLU: 42, GSM8K: 35.3.

Arxiv:2305.18290 Conversational Dataset:allenai/ultrafeedback ... Dataset:hkust-nlp/deita-10k-v0 Dataset:huggingfaceh4/ultracha... Dataset:intel/orca dpo pairs Dataset:ldjnr/capybara Dataset:meta-math/metamathqa Dataset:openchat/openchat shar... Dataset:wizardlm/wizardlm evol... En Endpoints compatible Gguf Instruct Q4 Quantized Region:us Safetensors Stablelm

Model Card on HF 🤗: https://huggingface.co/stabilityai/stablelm-2-zephyr-1_6b

Stablelm 2 Zephyr 1 6b Benchmarks

ARC: 43.69 vs 96.7 (so35)^-54.8%

HellaSwag: 69.3 vs 95.3 (gpt4)^-27.3%

MMLU: 42.03 vs 88.3 (so35)^-52.4%

GSM8K: 35.33 vs 96.4 (so35)^-63.4%

LLME Score: 0.20211

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Stablelm 2 Zephyr 1 6B (stabilityai/stablelm-2-zephyr-1_6b)

🌟 Advertise your project 🚀

Stablelm 2 Zephyr 1 6B Parameters and Internals

LLM Name	Stablelm 2 Zephyr 1 6b
Repository 🤗	https://huggingface.co/stabilityai/stablelm-2-zephyr-1_6b
Base Model(s)	Stablelm 2 Zephyr 1 6b Xenova/stablelm-2-zephyr-1_6b
Model Size	6b
Required VRAM	1 GB
Updated	2026-05-20
Maintainer	stabilityai
Model Type	stablelm
Instruction-Based	Yes
Model Files	3.3 GB 1.1 GB 1.0 GB 1.1 GB 1.2 GB 1.8 GB 3.3 GB
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	gguf\|q4\|q5_k
Model Architecture	StableLmForCausalLM
License	other
Context Length	4096
Model Max Length	4096
Transformers Version	4.38.0
Tokenizer Class	GPT2TokenizerFast
Padding Token	<\|endoftext\|>
Vocabulary Size	100352
Torch Data Type	float16

Quantized Models of the Stablelm 2 Zephyr 1 6B

Model	Likes	Downloads	VRAM
Stablelm 2 Zephyr 1.6B GGUF	15	974	0 GB

Best Alternatives to Stablelm 2 Zephyr 1 6B

Best Alternatives	Context / RAM	Downloads	Likes
Stablelm 2 Zephyr 1.6B GGUF	4K / 0.7 GB	974	15
Stablelm 2 Zephyr 1 6b 4bit	4K / 1.2 GB	50	5
Stablelm 2 1 6b Chat	4K / 6.6 GB	1165	35
Stablelm 2 Zephyr 1 6b	4K / 3.3 GB	17	1

Rank the Stablelm 2 Zephyr 1 6B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 53972 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Stablelm 2 Zephyr 1 6B by stabilityai