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

FusionNet 34Bx2 MoE GGUF by TheBloke

 »  All LLMs  »  TheBloke  »  FusionNet 34Bx2 MoE GGUF   URL Share it on

  215   
Base model:quantized:tomgrc/fu... Base model:tomgrc/fusionnet 34...   Conversational   En   Gguf   Mixtral   Moe   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/TheBloke/FusionNet_34Bx2_MoE-GGUF 

FusionNet 34Bx2 MoE GGUF Benchmarks

LLME Score: 0.16883
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
FusionNet 34Bx2 MoE GGUF (TheBloke/FusionNet_34Bx2_MoE-GGUF)

FusionNet 34Bx2 MoE GGUF Parameters and Internals

Model Type 
mixtral
Additional Notes 
Fine-tuned model on English language using MoE method. This model is fine-tuned to experiment with the MoE method, which could significantly increase performance.
LLM NameFusionNet 34Bx2 MoE GGUF
Repository 🤗https://huggingface.co/TheBloke/FusionNet_34Bx2_MoE-GGUF 
Model NameFusionNet 34Bx2 MoE
Model CreatorSuqin Zhang
Base Model(s)  FusionNet 34Bx2 MoE   TomGrc/FusionNet_34Bx2_MoE
Required VRAM22.4 GB
Updated2025-02-05
MaintainerTheBloke
Model Typemixtral
Model Files  22.4 GB   31.8 GB   29.2 GB   26.3 GB   34.3 GB   36.7 GB   34.6 GB   41.9 GB   43.1 GB   41.9 GB   49.9 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModel
Licensemit

Best Alternatives to FusionNet 34Bx2 MoE GGUF

Best Alternatives
Context / RAM
Downloads
Likes
ComicBot V.2 Gguf32K / 5 GB230
Phi 2 GGUF0K / 1.2 GB2200309195
Marco O1 GGUF0K / 3 GB50112
...ixtral 8x7B Instruct V0.1 GGUF0K / 15.6 GB37350611
Mixtral 8x7B V0.1 GGUF0K / 15.6 GB4950423
Dolphin 2.7 Mixtral 8x7b GGUF0K / 15.6 GB8747138
Dolphin 2.5 Mixtral 8x7b GGUF0K / 15.6 GB6026300
GOAT Llama3.1 V0.10K / 0.2 GB103
Phi 3 Mini 4K Instruct GGUF0K / 1.4 GB93416
Futfut By Zephyr7b Gguf0K / 5.1 GB1912
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/FusionNet_34Bx2_MoE-GGUF.

Rank the FusionNet 34Bx2 MoE GGUF 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? 42625 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.
Release v20241227
  Support LLM Explorer