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

Wolfram Miqu 1 120B 4.0bpw H6 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  Wolfram Miqu 1 120B 4.0bpw H6 EXL2   URL Share it on

  8   
  Autotrain compatible Base model:152334h/miqu-1-70b-... Base model:finetune:152334h/mi...   Conversational   De   En   Endpoints compatible   Es   Exl2   Fr   It   Llama   Merge   Mergekit   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoneStriker/wolfram_miqu-1-120b-4.0bpw-h6-exl2 

Wolfram Miqu 1 120B 4.0bpw H6 EXL2 Benchmarks

LLME Score: 0.13532
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Wolfram Miqu 1 120B 4.0bpw H6 EXL2 (LoneStriker/wolfram_miqu-1-120b-4.0bpw-h6-exl2)
🌟 Advertise your project 🚀

Wolfram Miqu 1 120B 4.0bpw H6 EXL2 Parameters and Internals

Additional Notes 
This model was created using mergekit by interleaving layers of miqu-1-70b-sf with itself. It draws inspiration from other models like Venus-120b-v1.2, MegaDolphin-120b, and goliath-120b.
Supported Languages 
English (Supported), German (Supported), French (Supported), Spanish (Supported), Italian (Supported)
Training Details 
Methodology:
This is a 120b frankenmerge of miqu-1-70b created by interleaving layers of miqu-1-70b-sf with itself using mergekit.
Context Length:
32764
Input Output 
Input Format:
~~[INST] {prompt} [/INST]
LLM NameWolfram Miqu 1 120B 4.0bpw H6 EXL2
Repository 🤗https://huggingface.co/LoneStriker/wolfram_miqu-1-120b-4.0bpw-h6-exl2 
Base Model(s)  Miqu 1 70B Sf   152334H/miqu-1-70b-sf
Model Size70b
Required VRAM60.6 GB
Updated2025-09-23
MaintainerLoneStriker
Model Typellama
Model Files  8.5 GB: 1-of-8   8.6 GB: 2-of-8   8.5 GB: 3-of-8   8.5 GB: 4-of-8   8.6 GB: 5-of-8   8.5 GB: 6-of-8   8.5 GB: 7-of-8   0.9 GB: 8-of-8
Supported Languagesen de fr es it
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Context Length32764
Model Max Length32764
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Wolfram Miqu 1 120B 4.0bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 8bit1024K / 75 GB285
...B Instruct Gradient 1048K 4bit1024K / 39.7 GB83
...B Instruct Gradient 1048K 2bit1024K / 21.9 GB172
...0B Instruct Gradient 262K 4bit256K / 39.7 GB103
...0B Instruct Gradient 262K 8bit256K / 75 GB52
...0B Instruct Gradient 262K 2bit256K / 21.9 GB91
... Gradient 262K 2.25bpw H6 EXL2256K / 22.2 GB80
...t Gradient 262K 3.5bpw H6 EXL2256K / 32.9 GB60
...t Gradient 262K 4.0bpw H6 EXL2256K / 37.2 GB11
...t Gradient 262K 2.4bpw H6 EXL2256K / 23.5 GB50
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/wolfram_miqu-1-120b-4.0bpw-h6-exl2.

Rank the Wolfram Miqu 1 120B 4.0bpw 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? 51544 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 v20241124
  Support LLM Explorer