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

Sophosympatheia Midnight Miqu 70B V1.0 GPTQ32G by Kotokin

 »  All LLMs  »  Kotokin  »  Sophosympatheia Midnight Miqu 70B V1.0 GPTQ32G   URL Share it on

  9   

Sophosympatheia Midnight Miqu 70B V1.0 GPTQ32G is an open-source language model by Kotokin. Features: 70b LLM, VRAM: 40.7GB, Context: 31K, Quantized, LLM Explorer Score: 0.12.

  Arxiv:2307.11760   4bit   Conversational   Endpoints compatible   Gptq   Llama   Merge   Mergekit   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/Kotokin/sophosympatheia_Midnight-Miqu-70B-v1.0_GPTQ32G 

Sophosympatheia Midnight Miqu 70B V1.0 GPTQ32G Benchmarks

LLME Score: 0.12226
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Sophosympatheia Midnight Miqu 70B V1.0 GPTQ32G (Kotokin/sophosympatheia_Midnight-Miqu-70B-v1.0_GPTQ32G)
🌟 Advertise your project 🚀

Sophosympatheia Midnight Miqu 70B V1.0 GPTQ32G Parameters and Internals

Model Type 
text generation, roleplaying, storytelling
Use Cases 
Areas:
personal use, roleplaying, storytelling
Applications:
creative writing, roleplaying games
Primary Use Cases:
roleplaying interactions, story creation
Limitations:
performance not tested in other areas
Considerations:
Be aware of the risks of using a model with leaked weights.
Additional Notes 
The model incorporates features from both Midnight Rose and Miqu with improved long-context support.
Input Output 
Accepted Modalities:
text
Performance Tips:
Experiment with settings such as Quadratic Sampling and Min-P for creative outcomes. Adjust alpha_rope for context extension.
LLM NameSophosympatheia Midnight Miqu 70B V1.0 GPTQ32G
Repository 🤗https://huggingface.co/Kotokin/sophosympatheia_Midnight-Miqu-70B-v1.0_GPTQ32G 
Model Size70b
Required VRAM40.7 GB
Updated2026-03-29
MaintainerKotokin
Model Typellama
Model Files  40.7 GB
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureLlamaForCausalLM
Context Length32764
Model Max Length32764
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Sophosympatheia Midnight Miqu 70B V1.0 GPTQ32G

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB2796
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB190
...ama 3.1 70B Instruct Gptq 4bit128K / 39.9 GB244
Opus V1.2 70B Marlin32K / 36.4 GB50
MoMo 70B Lora 1.8.6 DPO GPTQ32K / 41.3 GB41
MoMo 70B Lora 1.8.4 DPO GPTQ32K / 41.3 GB21
Tess 70B V1.6 Marlin31K / 36.3 GB71
Midnight Miqu 70B V1.5 GPTQ32G31K / 40.7 GB464
Senku 70B GPTQ 4bit31K / 36.7 GB41
Miqu 1 70B Sf GPTQ31K / 36.7 GB2710
Note: green Score (e.g. "73.2") means that the model is better than Kotokin/sophosympatheia_Midnight-Miqu-70B-v1.0_GPTQ32G.

Rank the Sophosympatheia Midnight Miqu 70B V1.0 GPTQ32G 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? 52721 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