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

Sixtyoneeighty 4x7B V1 by jambroz

 »  All LLMs  »  jambroz  »  Sixtyoneeighty 4x7B V1   URL Share it on

  109   

Sixtyoneeighty 4x7B V1 is an open-source language model by jambroz. Features: 24.2b LLM, VRAM: 48.3GB, Context: 32K, License: apache-2.0, MoE, Instruction-Based, Code Generating, HF Score: 65.7, LLM Explorer Score: 0.14, Arc: 64.8, HellaSwag: 84.3, MMLU: 62.6, TruthfulQA: 56.2, WinoGrande: 80.4, GSM8K: 45.9.

Base model:chihoonlee10/t3q-mi... Base model:jambroz/sixtyoneeig... Base model:merge:chihoonlee10/... Base model:merge:jambroz/sixty... Base model:merge:neuralnovel/m... Base model:merge:s-miguel/the-... Base model:neuralnovel/mistral... Base model:s-miguel/the-trinit...   Codegen   Conversational   Endpoints compatible   Frankenmoe   Instruct   Jambroz/sixtyoneeighty-7b-chat   Lazymergekit   Merge   Mergekit   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/jambroz/sixtyoneeighty-4x7B-v1 

Sixtyoneeighty 4x7B V1 Benchmarks

ARC: 64.76 vs 96.7 (so35)-33%
HellaSwag: 84.26 vs 95.3 (gpt4)-11.6%
MMLU: 62.63 vs 88.3 (so35)-29.1%
TruthfulQA: 56.2 vs 59 (gpt4)-4.7%
WinoGrande: 80.43 vs 87.5 (gpt4)-8.1%
GSM8K: 45.94 vs 96.4 (so35)-52.3%
LLME Score: 0.14413
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Sixtyoneeighty 4x7B V1 (jambroz/sixtyoneeighty-4x7B-v1)
🌟 Advertise your project 🚀

Sixtyoneeighty 4x7B V1 Parameters and Internals

Model Type 
moe
Additional Notes 
sixtyoneeighty-7b-MOE is a Mixture of Experts model created using LazyMergekit from several base models including jambroz/sixtyoneeighty-7b-chat, NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story, S-miguel/The-Trinity-Coder-7B, and chihoonlee10/T3Q-Mistral-Orca-Math-DPO.
LLM NameSixtyoneeighty 4x7B V1
Repository 🤗https://huggingface.co/jambroz/sixtyoneeighty-4x7B-v1 
Base Model(s)  jambroz/sixtyoneeighty-7b-chat   NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story   The Trinity Coder 7B   T3Q Mistral Orca Math DPO   jambroz/sixtyoneeighty-7b-chat   NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story   S-miguel/The-Trinity-Coder-7B   chihoonlee10/T3Q-Mistral-Orca-Math-DPO
Model Size24.2b
Required VRAM48.3 GB
Updated2026-03-29
Maintainerjambroz
Model Typemixtral
Instruction-BasedYes
Model Files  9.9 GB: 1-of-5   10.0 GB: 2-of-5   10.0 GB: 3-of-5   10.0 GB: 4-of-5   8.4 GB: 5-of-5
Generates CodeYes
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.39.3
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32002
Torch Data Typebfloat16

Best Alternatives to Sixtyoneeighty 4x7B V1

Best Alternatives
Context / RAM
Downloads
Likes
Sixtyoneeighty 4x7B V232K / 48.3 GB00

Rank the Sixtyoneeighty 4x7B V1 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? 52721 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