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

Mixtral 34Bx2 MoE 60B 3.0bpw H6 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  Mixtral 34Bx2 MoE 60B 3.0bpw H6 EXL2   URL Share it on

  8   
  Autotrain compatible   Endpoints compatible   Exl2   Mixtral   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoneStriker/Mixtral_34Bx2_MoE_60B-3.0bpw-h6-exl2 

Mixtral 34Bx2 MoE 60B 3.0bpw H6 EXL2 Benchmarks

LLME Score: 0.15829
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mixtral 34Bx2 MoE 60B 3.0bpw H6 EXL2 (LoneStriker/Mixtral_34Bx2_MoE_60B-3.0bpw-h6-exl2)

Mixtral 34Bx2 MoE 60B 3.0bpw H6 EXL2 Parameters and Internals

Model Type 
MoE, causal language model
Use Cases 
Areas:
research, non-commercial applications
Applications:
text generation, multilingual applications
Primary Use Cases:
creative writing, storytelling, education
Limitations:
commercial applications
Supported Languages 
English (high), Chinese (high)
Input Output 
Input Format:
text prompt
Accepted Modalities:
text
Output Format:
generated text
Performance Tips:
For better performance, use a GPU with CUDA support.
LLM NameMixtral 34Bx2 MoE 60B 3.0bpw H6 EXL2
Repository 🤗https://huggingface.co/LoneStriker/Mixtral_34Bx2_MoE_60B-3.0bpw-h6-exl2 
Model Size60b
Required VRAM23.8 GB
Updated2025-02-05
MaintainerLoneStriker
Model Typemixtral
Model Files  8.6 GB: 1-of-3   8.6 GB: 2-of-3   6.6 GB: 3-of-3
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 Mixtral 34Bx2 MoE 60B 3.0bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
... 34Bx2 MoE 60B 2.65bpw H6 EXL2195K / 21.2 GB61
...i 34Bx2 MoE 60B 5.0bpw H6 EXL2195K / 38.8 GB51
...i 34Bx2 MoE 60B 6.0bpw H6 EXL2195K / 46.2 GB41
...l 34Bx2 MoE 60B 8.0bpw H8 EXL2195K / 61.3 GB42
...l 34Bx2 MoE 60B 2.4bpw H6 EXL2195K / 19.3 GB53
... 34Bx2 MoE 60B 4.65bpw H6 EXL2195K / 36.2 GB41
...l 34Bx2 MoE 60B EXL2 2.0bpw H8195K / 18.1 GB71
... 34Bx2 MoE 60B 2.65bpw H6 EXL2195K / 21.2 GB42
...l 34Bx2 MoE 60B 4.0bpw H6 EXL2195K / 31.3 GB52
...l 34Bx2 MoE 60B 6.0bpw H6 EXL2195K / 46.2 GB61
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Mixtral_34Bx2_MoE_60B-3.0bpw-h6-exl2.

Rank the Mixtral 34Bx2 MoE 60B 3.0bpw 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? 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