LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

NearalMistral 2x7B by Corianas

 »  All LLMs  »  Corianas  »  NearalMistral 2x7B   URL Share it on

  69   

NearalMistral 2x7B is an open-source language model by Corianas. Features: 12.9b LLM, VRAM: 25.8GB, Context: 32K, License: apache-2.0, MoE, Instruction-Based, LLM Explorer Score: 0.14, Arc: 57.4, HellaSwag: 77.7, MMLU: 56.5, GSM8K: 31.6.

Base model:corianas/neural-mis... Base model:merge:corianas/neur... Base model:merge:mistralai/mis... Base model:mistralai/mistral-7...   Conversational   Corianas/neural-mistral-7b   Endpoints compatible   Frankenmoe   Instruct   Lazymergekit   Merge   Mergekit Mistralai/mistral-7b-instruct-...   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Corianas/NearalMistral-2x7B 

NearalMistral 2x7B Benchmarks

ARC: 57.42 vs 96.7 (so35)-40.6%
HellaSwag: 77.67 vs 95.3 (gpt4)-18.5%
MMLU: 56.46 vs 88.3 (so35)-36.1%
GSM8K: 31.61 vs 96.4 (so35)-67.2%
LLME Score: 0.14123
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
NearalMistral 2x7B (Corianas/NearalMistral-2x7B)
🌟 Advertise your project 🚀

NearalMistral 2x7B Parameters and Internals

Model Type 
Mixture of Experts (MoE)
Additional Notes 
Built using LazyMergekit.
LLM NameNearalMistral 2x7B
Repository 🤗https://huggingface.co/Corianas/NearalMistral-2x7B 
Base Model(s)  mistralai/Mistral-7B-Instruct-v0.1   Neural Mistral 7B   mistralai/Mistral-7B-Instruct-v0.1   Corianas/Neural-Mistral-7B
Model Size12.9b
Required VRAM25.8 GB
Updated2026-05-21
MaintainerCorianas
Model Typemixtral
Instruction-BasedYes
Model Files  9.9 GB: 1-of-3   10.0 GB: 2-of-3   5.9 GB: 3-of-3
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to NearalMistral 2x7B

Best Alternatives
Context / RAM
Downloads
Likes
Inf Silent Kunoichi V0.1 2x7B32K / 25.6 GB60
Inf Silent Kunoichi V0.2 2x7B32K / 25.6 GB101
Megatron V3 2x7B32K / 25.8 GB713
MistarlingMaid 2x7B Base32K / 25.8 GB940
MergedExpert 2x8b32K / 25.8 GB50
MergedExperts 2x8b32K / 25.8 GB60
...afted Hermetic Platypus C 2x7B32K / 25.8 GB940
...tral 7B Instruct V0.2 2x7B MoE32K / 25.8 GB11314
...tral Instruct MoE Experimental32K / 25.8 GB1002
Mistral 2x7b V0.132K / 25.8 GB101
Note: green Score (e.g. "73.2") means that the model is better than Corianas/NearalMistral-2x7B.

Rank the NearalMistral 2x7B 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? 53885 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