What are the hardware requirements for OpenHermes 2.5 Mistral 7B?

OpenHermes 2.5 Mistral 7B requires approximately 14.4 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed OpenHermes 2.5 Mistral 7B and how large is it?

OpenHermes 2.5 Mistral 7B is developed by teknium, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does OpenHermes 2.5 Mistral 7B perform on standard benchmarks?

OpenHermes 2.5 Mistral 7B has the following published scores: MMLU 63.82, LMSYS ELO 1089. Compare against reference models on this page or on the LLM Explorer leaderboards.

OpenHermes 2.5 Mistral 7B by teknium — VRAM 14.4GB, 32K context

Name: OpenHermes 2.5 Mistral 7B
Rating: 3 (6 reviews)
Author: teknium

OpenHermes 2.5 Mistral 7B is an open-source language model by teknium. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: apache-2.0, HF Score: 61.5, LLM Explorer Score: 0.39, ELO: 1089, Arc: 64.9, HellaSwag: 84.3, MMLU: 63.8, TruthfulQA: 52.3, WinoGrande: 77.9, GSM8K: 25.5.

Base model:finetune:mistralai/... Base model:mistralai/mistral-7... Chatml Conversational Dataset:teknium/openhermes-2.5 Deploy:azure Distillation En Endpoints compatible Finetuned Gpt4 Instruct Mistral Pytorch Region:us Safetensors Sharded Synthetic data Tensorflow

Model Card on HF 🤗: https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B

OpenHermes 2.5 Mistral 7B Benchmarks

LMSys ELO: 1089 vs 1272 (so35)^-14.4%

IFEval: 55.71 vs 88 (so35)^-36.7%

ARC: 64.93 vs 96.7 (so35)^-32.9%

HellaSwag: 84.3 vs 95.3 (gpt4)^-11.5%

MMLU: 63.82 vs 88.3 (so35)^-27.7%

TruthfulQA: 52.31 vs 59 (gpt4)^-11.3%

WinoGrande: 77.9 vs 87.5 (gpt4)^-11%

GSM8K: 25.47 vs 96.4 (so35)^-73.6%

MATH Lvl 5: 5.06

LLME Score: 0.3881

^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)

OpenHermes 2.5 Mistral 7B (teknium/OpenHermes-2.5-Mistral-7B)

🌟 Advertise your project 🚀

OpenHermes 2.5 Mistral 7B Parameters and Internals

Model Type

text generation

Use Cases

Areas:

research, commercial applications

Applications:

chat systems, programming support, general AI applications

Primary Use Cases:

general conversation, programming assistance, interactive storytelling

Limitations:

reduced performance on BigBench benchmark

Considerations:

Be cautious of AI bias and ensure safety measures.

Additional Notes

New system prompts engage assistants in multi-turn dialogues with ChatML format.

Supported Languages

en (English)

Training Details

Data Sources:

GPT-4 generated data, teknium/OpenHermes-2.5

Data Volume:

1,000,000 entries

Methodology:

Extensive filtering and conversion to ShareGPT, transformed by axolotl to use ChatML.

Input Output

Input Format:

ChatML

Accepted Modalities:

text

Output Format:

text

Performance Tips:

Use the ChatML prompt format for better multi-turn chat engagement.

LLM Name	OpenHermes 2.5 Mistral 7B
Repository 🤗	https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B
Base Model(s)	mistralai/Mistral-7B-v0.1 mistralai/Mistral-7B-v0.1
Model Size	7b
Required VRAM	14.4 GB
Updated	2026-04-13
Maintainer	teknium
Model Type	mistral
Model Files	9.9 GB: 1-of-2 4.5 GB: 2-of-2 9.9 GB: 1-of-2 4.5 GB: 2-of-2
Supported Languages	en
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.34.0.dev0
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32002
Torch Data Type	bfloat16

Quantized Models of the OpenHermes 2.5 Mistral 7B

Model	Likes	Downloads	VRAM
...enHermes 2.5 Mistral 7B Marlin	2	15	4 GB
OpenHermes 2.5 Mistral 7B GGUF	276	11462	3 GB
OpenHermes 2.5 Mistral 7B AWQ	21	22754	4 GB
Unsloth OpenHermes F16	0	11	14 GB
...rix Philosophy Mistral 7B LoRA	9	1317	14 GB
...us Hermes 2 Mistral 7B DPO AWQ	8	15	4 GB
...enHermes 2.5 Mistral 7B Marlin	2	680	4 GB
...Hermes 2.5 Mistral 7B Hun GGUF	2	21	4 GB
...Mistral 7B Alpaca Cleaned GGUF	0	20	7 GB
OpenHermes 2.5 Mistral 7B GGUF	2	891	2 GB

Best Alternatives to OpenHermes 2.5 Mistral 7B

Best Alternatives	Context / RAM	Downloads	Likes
...Nemo Instruct 2407 Abliterated	1000K / 24.5 GB	254	20
MegaBeam Mistral 7B 512K	512K / 14.4 GB	11443	54
SpydazWeb AI HumanAI RP	512K / 14.4 GB	21	1
SpydazWeb AI HumanAI 002	512K / 14.4 GB	18	1
...daz Web AI ChatML 512K Project	512K / 14.5 GB	12	0
MegaBeam Mistral 7B 300K	282K / 14.4 GB	3779	16
MegaBeam Mistral 7B 300K	282K / 14.4 GB	7968	16
Hebrew Mistral 7B 200K	256K / 30 GB	1316	15
Astral 256K 7B V2	250K / 14.4 GB	10	0
Astral 256K 7B	250K / 14.4 GB	5	0

Rank the OpenHermes 2.5 Mistral 7B 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? 53286 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

OpenHermes 2.5 Mistral 7B by teknium