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

Midnight Miqu 103B V1.0 EXL2 4.5bpw by Dracones

 »  All LLMs  »  Dracones  »  Midnight Miqu 103B V1.0 EXL2 4.5bpw   URL Share it on

  9   
  Autotrain compatible   Conversational   Endpoints compatible   Exl2   Llama   Merge   Mergekit   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Dracones/Midnight-Miqu-103B-v1.0_exl2_4.5bpw 

Midnight Miqu 103B V1.0 EXL2 4.5bpw Benchmarks

LLME Score: 0.15565
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Midnight Miqu 103B V1.0 EXL2 4.5bpw (Dracones/Midnight-Miqu-103B-v1.0_exl2_4.5bpw)

Midnight Miqu 103B V1.0 EXL2 4.5bpw Parameters and Internals

Model Type 
mergekit, merge
Additional Notes 
This model is a 4.5bpw EXL2 quantization of the base model.
LLM NameMidnight Miqu 103B V1.0 EXL2 4.5bpw
Repository 🤗https://huggingface.co/Dracones/Midnight-Miqu-103B-v1.0_exl2_4.5bpw 
Model Size103b
Required VRAM58.7 GB
Updated2025-05-31
MaintainerDracones
Model Typellama
Model Files  8.5 GB: 1-of-7   8.6 GB: 2-of-7   8.6 GB: 3-of-7   8.6 GB: 4-of-7   8.6 GB: 5-of-7   8.6 GB: 6-of-7   7.2 GB: 7-of-7
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Context Length32764
Model Max Length32764
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Midnight Miqu 103B V1.0 EXL2 4.5bpw

Best Alternatives
Context / RAM
Downloads
Likes
... Dark Miqu 103B 5.0bpw H8 EXL231K / 65.1 GB170
...qu 103B V1.5 EXL2 5.0bpw Rpcal31K / 64.9 GB521
...qu 103B V1.5 EXL2 3.0bpw Rpcal31K / 39.3 GB201
... Miqu 103B V1.5 3.5bpw H6 EXL231K / 45.6 GB91
...qu 103B V1.5 EXL2 4.0bpw Rpcal31K / 52.1 GB121
...ht Miqu 103B V1.0 EXL2 4.25bpw31K / 55.3 GB211
...ght Miqu 103B V1.0 EXL2 4.0bpw31K / 52.2 GB191
...ght Miqu 103B V1.0 EXL2 5.0bpw31K / 64.9 GB291
...ght Miqu 103B V1.0 EXL2 3.0bpw31K / 39.2 GB112
...ght Miqu 103B V1.0 EXL2 2.4bpw31K / 31.6 GB111
Note: green Score (e.g. "73.2") means that the model is better than Dracones/Midnight-Miqu-103B-v1.0_exl2_4.5bpw.

Rank the Midnight Miqu 103B V1.0 EXL2 4.5bpw 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? 47753 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