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

4bit Quant TomGrc FusionNet 34Bx2 MoE V0.1 DPO by cloudyu

 »  All LLMs  »  cloudyu  »  4bit Quant TomGrc FusionNet 34Bx2 MoE V0.1 DPO   URL Share it on

  105   

4bit Quant TomGrc FusionNet 34Bx2 MoE V0.1 DPO is an open-source language model by cloudyu. Features: 61.7b LLM, VRAM: 35.6GB, Context: 195K, License: apache-2.0, MoE, Quantized, HF Score: 77, LLM Explorer Score: 0.12, Arc: 73.2, HellaSwag: 86.1, MMLU: 75.4, TruthfulQA: 72.8, WinoGrande: 83, GSM8K: 71.2.

  4-bit   4bit   Bitsandbytes   Conversational   Endpoints compatible   Mixtral   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Yi
Model Card on HF 🤗: https://huggingface.co/cloudyu/4bit_quant_TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO 

4bit Quant TomGrc FusionNet 34Bx2 MoE V0.1 DPO Benchmarks

ARC: 73.21 vs 96.7 (so35)-24.3%
HellaSwag: 86.11 vs 95.3 (gpt4)-9.6%
MMLU: 75.44 vs 88.3 (so35)-14.6%
TruthfulQA: 72.78 vs 59 (gpt4)23.4%
WinoGrande: 82.95 vs 87.5 (gpt4)-5.2%
GSM8K: 71.19 vs 96.4 (so35)-26.2%
LLME Score: 0.1233
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
4bit Quant TomGrc FusionNet 34Bx2 MoE V0.1 DPO (cloudyu/4bit_quant_TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO)
🌟 Advertise your project 🚀

4bit Quant TomGrc FusionNet 34Bx2 MoE V0.1 DPO Parameters and Internals

Model Type 
language model
Training Details 
Methodology:
Uses TRL's DPO Trainer: Direct Preference Optimization
Model Architecture:
MoE (Mixture of Experts)
LLM Name4bit Quant TomGrc FusionNet 34Bx2 MoE V0.1 DPO
Repository 🤗https://huggingface.co/cloudyu/4bit_quant_TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO 
Model Size61.7b
Required VRAM35.6 GB
Updated2026-03-30
Maintainercloudyu
Model Typemixtral
Model Files  5.0 GB: 1-of-8   5.0 GB: 2-of-8   5.0 GB: 3-of-8   5.0 GB: 4-of-8   5.0 GB: 5-of-8   5.0 GB: 6-of-8   4.7 GB: 7-of-8   0.9 GB: 8-of-8
Quantization Type4bit
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length200000
Model Max Length200000
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size64000
Torch Data Typebfloat16

Best Alternatives to 4bit Quant TomGrc FusionNet 34Bx2 MoE V0.1 DPO

Best Alternatives
Context / RAM
Downloads
Likes
60B MoE Coder V2195K / 35.6 GB861

Rank the 4bit Quant TomGrc FusionNet 34Bx2 MoE V0.1 DPO 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