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

Yi 34Bx2 MoE 60B 5.0bpw H6 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  Yi 34Bx2 MoE 60B 5.0bpw H6 EXL2   URL Share it on

  3   

Yi 34Bx2 MoE 60B 5.0bpw H6 EXL2 is an open-source language model by LoneStriker. Features: 60b LLM, VRAM: 38.8GB, Context: 195K, License: cc-by-nc-4.0, MoE, Quantized, LLM Explorer Score: 0.11.

  Conversational   Endpoints compatible   Exl2   Mixtral   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoneStriker/Yi-34Bx2-MoE-60B-5.0bpw-h6-exl2 

Yi 34Bx2 MoE 60B 5.0bpw H6 EXL2 Benchmarks

LLME Score: 0.11438
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Yi 34Bx2 MoE 60B 5.0bpw H6 EXL2 (LoneStriker/Yi-34Bx2-MoE-60B-5.0bpw-h6-exl2)
🌟 Advertise your project 🚀

Yi 34Bx2 MoE 60B 5.0bpw H6 EXL2 Parameters and Internals

Model Type 
Mixture of Experts (MoE), Causal Language Model
Use Cases 
Areas:
research, non-commercial applications
Additional Notes 
The Yi based MOE 2x34B model is a slightly different version of cloudyu/Mixtral_34Bx2_MoE_60B and integrates elements from jondurbin/bagel-dpo-34b-v0.2 and SUSTech/SUS-Chat-34B models.
Supported Languages 
English (proficient), Chinese (proficient)
Input Output 
Input Format:
Textual prompts
Accepted Modalities:
text
Output Format:
Text
Performance Tips:
Ensure that the input prompt is in English or Chinese for best performance.
LLM NameYi 34Bx2 MoE 60B 5.0bpw H6 EXL2
Repository 🤗https://huggingface.co/LoneStriker/Yi-34Bx2-MoE-60B-5.0bpw-h6-exl2 
Model Size60b
Required VRAM38.8 GB
Updated2026-03-30
MaintainerLoneStriker
Model Typemixtral
Model Files  8.6 GB: 1-of-5   8.6 GB: 2-of-5   8.5 GB: 3-of-5   8.6 GB: 4-of-5   4.5 GB: 5-of-5
Quantization Typeexl2
Model ArchitectureMixtralForCausalLM
Licensecc-by-nc-4.0
Context Length200000
Model Max Length200000
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size64000
Torch Data Typebfloat16

Best Alternatives to Yi 34Bx2 MoE 60B 5.0bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
... 34Bx2 MoE 60B 2.65bpw H6 EXL2195K / 21.2 GB31
...i 34Bx2 MoE 60B 6.0bpw H6 EXL2195K / 46.2 GB31
...l 34Bx2 MoE 60B 8.0bpw H8 EXL2195K / 61.3 GB22
... 34Bx2 MoE 60B 4.65bpw H6 EXL2195K / 36.2 GB151
...l 34Bx2 MoE 60B 2.4bpw H6 EXL2195K / 19.3 GB23
... 34Bx2 MoE 60B 2.65bpw H6 EXL2195K / 21.2 GB12
...l 34Bx2 MoE 60B EXL2 2.0bpw H8195K / 18.1 GB31
...l 34Bx2 MoE 60B 4.0bpw H6 EXL2195K / 31.3 GB52
...l 34Bx2 MoE 60B 3.0bpw H6 EXL2195K / 23.8 GB22
...l 34Bx2 MoE 60B 6.0bpw H6 EXL2195K / 46.2 GB31

Rank the Yi 34Bx2 MoE 60B 5.0bpw H6 EXL2 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