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

Stablelm 2 1 6B Chat requires approximately 6.6 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 1 6B Chat and how large is it?

Stablelm 2 1 6B Chat 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 1 6B Chat perform on standard benchmarks?

Stablelm 2 1 6B Chat has the following published scores: MMLU 41.47. Compare against reference models on this page or on the LLM Explorer leaderboards.

Stablelm 2 1 6B Chat by stabilityai — VRAM 6.6GB, 4K context

Name: Stablelm 2 1 6B Chat
Author: stabilityai

Stablelm 2 1 6B Chat is an open-source language model by stabilityai. Features: 6b LLM, VRAM: 6.6GB, Context: 4K, License: other, Instruction-Based, LLM Explorer Score: 0.19, Arc: 43.5, HellaSwag: 69.2, MMLU: 41.5, GSM8K: 38.8.

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:teknium/openhermes-2.5 Dataset:wizardlm/wizardlm evol... En Endpoints compatible Instruct Region:us Safetensors Sharded Stablelm Tensorflow

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

Stablelm 2 1 6b Chat Benchmarks

ARC: 43.52 vs 96.7 (so35)^-55%

HellaSwag: 69.24 vs 95.3 (gpt4)^-27.3%

MMLU: 41.47 vs 88.3 (so35)^-53%

GSM8K: 38.82 vs 96.4 (so35)^-59.7%

LLME Score: 0.19127

^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 1 6B Chat (stabilityai/stablelm-2-1_6b-chat)

🌟 Advertise your project 🚀

Stablelm 2 1 6B Chat Parameters and Internals

Model Type

auto-regressive, transformer decoder

Use Cases

Primary Use Cases:

Chat-like applications

Limitations:

Limited adversarial input training, Potential for misinformation and harmful outputs

Considerations:

Developers must evaluate the model for safety performance. Use input/output classifier to prevent harmful responses.

Supported Languages

languages (English), proficiency ()

Training Details

Data Sources:

HuggingFaceH4/ultrachat_200k, meta-math/MetaMathQA, WizardLM/WizardLM_evol_instruct_V2_196k, Open-Orca/SlimOrca, openchat/openchat_sharegpt4_dataset, LDJnr/Capybara, hkust-nlp/deita-10k-v0, teknium/OpenHermes-2.5, allenai/ultrafeedback_binarized_cleaned, Intel/orca_dpo_pairs, argilla/dpo-mix-7k

Methodology:

Direct Preference Optimization (DPO)

Model Architecture:

Transformer decoder

LLM Name	Stablelm 2 1 6b Chat
Repository 🤗	https://huggingface.co/stabilityai/stablelm-2-1_6b-chat
Model Size	6b
Required VRAM	6.6 GB
Updated	2026-05-26
Maintainer	stabilityai
Model Type	stablelm
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 1.6 GB: 2-of-2
Supported Languages	en
Model Architecture	StableLmForCausalLM
License	other
Context Length	4096
Model Max Length	4096
Transformers Version	4.39.3
Tokenizer Class	GPT2TokenizerFast
Padding Token	<\|endoftext\|>
Vocabulary Size	100352
Torch Data Type	float32

Quantized Models of the Stablelm 2 1 6B Chat

Model	Likes	Downloads	VRAM
Vega 1 6B	0	8	6 GB

Best Alternatives to Stablelm 2 1 6B Chat

Best Alternatives	Context / RAM	Downloads	Likes
Stablelm 2 Zephyr 1 6b	4K / 3.3 GB	17	1
Stablelm 2 Zephyr 1 6b 4bit	4K / 1.2 GB	50	5
Stablelm 2 Zephyr 1 6b	4K / 1 GB	3986	187
Stablelm 2 Zephyr 1.6B GGUF	4K / 0.7 GB	974	15

Note: green Score (e.g. "73.2") means that the model is better than stabilityai/stablelm-2-1_6b-chat.

Rank the Stablelm 2 1 6B Chat 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? 53999 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 1 6B Chat by stabilityai