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

Midnight Miqu 70B V1.5 4bit by cecibas

 »  All LLMs  »  cecibas  »  Midnight Miqu 70B V1.5 4bit   URL Share it on

  228   

Midnight Miqu 70B V1.5 4bit is an open-source language model by cecibas. Features: 70b LLM, VRAM: 36.7GB, Context: 31K, License: unknown, Quantized, LLM Explorer Score: 0.14.

  4-bit   4bit   Awq   Conversational   Deploy:azure   Endpoints compatible   Llama   Pytorch   Quantized   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/cecibas/Midnight-Miqu-70B-v1.5-4bit 

Midnight Miqu 70B V1.5 4bit Benchmarks

LLME Score: 0.13829
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Midnight Miqu 70B V1.5 4bit (cecibas/Midnight-Miqu-70B-v1.5-4bit)
🌟 Advertise your project 🚀

Midnight Miqu 70B V1.5 4bit Parameters and Internals

Model Type 
awq quant
LLM NameMidnight Miqu 70B V1.5 4bit
Repository 🤗https://huggingface.co/cecibas/Midnight-Miqu-70B-v1.5-4bit 
Base Model(s)  sophosympatheia/Midnight-Miqu-70B-v1.5   sophosympatheia/Midnight-Miqu-70B-v1.5
Model Size70b
Required VRAM36.7 GB
Updated2026-05-23
Maintainercecibas
Model Typellama
Model Files  1.9 GB: 1-of-19   1.9 GB: 2-of-19   1.9 GB: 3-of-19   2.0 GB: 4-of-19   1.9 GB: 5-of-19   1.9 GB: 6-of-19   2.0 GB: 7-of-19   1.9 GB: 8-of-19   1.9 GB: 9-of-19   2.0 GB: 10-of-19   1.9 GB: 11-of-19   1.9 GB: 12-of-19   2.0 GB: 13-of-19   1.9 GB: 14-of-19   1.9 GB: 15-of-19   2.0 GB: 16-of-19   1.9 GB: 17-of-19   1.9 GB: 18-of-19   2.0 GB: 19-of-19
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licenseunknown
Context Length32764
Model Max Length32764
Transformers Version4.41.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Midnight Miqu 70B V1.5 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 8bit1024K / 75 GB375
...B Instruct Gradient 1048K 4bit1024K / 39.7 GB233
...B Instruct Gradient 1048K 2bit1024K / 21.9 GB452
...0B Instruct Gradient 262K 4bit256K / 39.7 GB253
...0B Instruct Gradient 262K 8bit256K / 75 GB152
...0B Instruct Gradient 262K 2bit256K / 21.9 GB211
... Gradient 262K 2.25bpw H6 EXL2256K / 22.2 GB80
...t Gradient 262K 2.4bpw H6 EXL2256K / 23.5 GB100
...t Gradient 262K 3.5bpw H6 EXL2256K / 32.9 GB60
...t Gradient 262K 4.0bpw H6 EXL2256K / 37.2 GB21

Rank the Midnight Miqu 70B V1.5 4bit 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? 53972 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