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

Miquliz 120B 4.0bpw H6 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  Miquliz 120B 4.0bpw H6 EXL2   URL Share it on

  7   

Miquliz 120B 4.0bpw H6 EXL2 is an open-source language model by LoneStriker. Features: 70b LLM, VRAM: 59.4GB, Context: 32K, Quantized, Merged, LLM Explorer Score: 0.12.

  Merged Model   Autotrain compatible Base model:152334h/miqu-1-70b-... Base model:lizpreciatior/lzlv ...   Conversational   De   En   Endpoints compatible   Es   Exl2   Fp16   Fr   It   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoneStriker/miquliz-120b-4.0bpw-h6-exl2 

Miquliz 120B 4.0bpw H6 EXL2 Benchmarks

LLME Score: 0.11867
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Miquliz 120B 4.0bpw H6 EXL2 (LoneStriker/miquliz-120b-4.0bpw-h6-exl2)
🌟 Advertise your project 🚀

Miquliz 120B 4.0bpw H6 EXL2 Parameters and Internals

Additional Notes 
This is a 120b frankenmerge created by interleaving layers of miqu-1-70b-sf with lzlv_70b_fp16_hf using mergekit. Inspired by goliath-120b.
Supported Languages 
en (fully supported), de (fully supported), fr (fully supported), es (fully supported), it (fully supported)
Training Details 
Methodology:
passthrough merge method
Context Length:
32768
Model Architecture:
Max Context: 32768 tokens, Layers: 137
Input Output 
Input Format:
~~[INST] {prompt} [/INST]
LLM NameMiquliz 120B 4.0bpw H6 EXL2
Repository 🤗https://huggingface.co/LoneStriker/miquliz-120b-4.0bpw-h6-exl2 
Base Model(s)  Miqu 1 70B Sf   Lzlv 70b Fp16 Hf   152334H/miqu-1-70b-sf   lizpreciatior/lzlv_70b_fp16_hf
Merged ModelYes
Model Size70b
Required VRAM59.4 GB
Updated2025-09-23
MaintainerLoneStriker
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   7.9 GB: 7-of-7
Supported Languagesen de fr es it
Quantization Typefp16|exl2
Model ArchitectureLlamaForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Miquliz 120B 4.0bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 8bit1024K / 75 GB445
...B Instruct Gradient 1048K 4bit1024K / 39.7 GB123
...B Instruct Gradient 1048K 2bit1024K / 21.9 GB172
...0B Instruct Gradient 262K 4bit256K / 39.7 GB183
...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 4.0bpw H6 EXL2256K / 37.2 GB41
...t Gradient 262K 3.5bpw H6 EXL2256K / 32.9 GB60
...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/miquliz-120b-4.0bpw-h6-exl2.

Rank the Miquliz 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? 52392 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