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

Miquella 120B 8.0bpw H8 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  Miquella 120B 8.0bpw H8 EXL2   URL Share it on

  11   
  Autotrain compatible   Endpoints compatible   Exl2   Llama   Merge   Mergekit   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoneStriker/miquella-120b-8.0bpw-h8-exl2 

Miquella 120B 8.0bpw H8 EXL2 Benchmarks

LLME Score: 0.17161
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Miquella 120B 8.0bpw H8 EXL2 (LoneStriker/miquella-120b-8.0bpw-h8-exl2)

Miquella 120B 8.0bpw H8 EXL2 Parameters and Internals

Model Type 
pre-trained language model
Additional Notes 
Model has been remade with fixed dequantization of miqu.
LLM NameMiquella 120B 8.0bpw H8 EXL2
Repository 🤗https://huggingface.co/LoneStriker/miquella-120b-8.0bpw-h8-exl2 
Model Size120b
Required VRAM118.1 GB
Updated2024-12-26
MaintainerLoneStriker
Model Typellama
Model Files  8.4 GB: 1-of-14   8.5 GB: 2-of-14   8.5 GB: 3-of-14   8.6 GB: 4-of-14   8.6 GB: 5-of-14   8.5 GB: 6-of-14   8.6 GB: 7-of-14   8.6 GB: 8-of-14   8.4 GB: 9-of-14   8.4 GB: 10-of-14   8.5 GB: 11-of-14   8.6 GB: 12-of-14   8.5 GB: 13-of-14   7.4 GB: 14-of-14
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Context Length32764
Model Max Length32764
Transformers Version4.37.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Miquella 120B 8.0bpw H8 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
Miquella 120B 3.0bpw H6 EXL231K / 44.8 GB1010
Miquella 120B 4.0bpw H6 EXL231K / 59.4 GB112
...t 120B Cat A Llama EXL2 5.5bpw8K / 85.3 GB150
...t 120B Cat A Llama EXL2 4.5bpw8K / 70.3 GB81
...h LongLORA 120B Rope8 32K Fp164K / 235.4 GB207
...RA 120B Rope8 32K 6bpw H8 EXL24K / 88.7 GB101
...egaDolphin 120B 2.9bpw H6 EXL24K / 44.3 GB183
...gaDolphin 120B 2.65bpw H6 EXL24K / 40.5 GB192
...egaDolphin 120B 4.0bpw H6 EXL24K / 60.8 GB171
Goliath 120B 6.0bpw H6 EXL24K / 88.9 GB161
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/miquella-120b-8.0bpw-h8-exl2.

Rank the Miquella 120B 8.0bpw H8 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? 40248 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 v20241217
  Support LLM Explorer