Senku 70B Full 2.4bpw H6 EXL2 by LoneStriker

 ยป  All LLMs  ยป  LoneStriker  ยป  Senku 70B Full 2.4bpw H6 EXL2   URL Share it on

  Autotrain compatible   Conversational   Endpoints compatible   Exl2   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Senku 70B Full 2.4bpw H6 EXL2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Senku 70B Full 2.4bpw H6 EXL2 (LoneStriker/Senku-70B-Full-2.4bpw-h6-exl2)
๐ŸŒŸ Advertise your project ๐Ÿš€

Senku 70B Full 2.4bpw H6 EXL2 Parameters and Internals

Additional Notes 
This model is a finetune and dequant of miqudev's leaked Mistral-70B model, alleged to be an early Mistral medium version.
LLM NameSenku 70B Full 2.4bpw H6 EXL2
Repository ๐Ÿค—https://huggingface.co/LoneStriker/Senku-70B-Full-2.4bpw-h6-exl2 
Model Size70b
Required VRAM21.3 GB
Updated2025-07-08
MaintainerLoneStriker
Model Typellama
Model Files  8.5 GB: 1-of-3   8.6 GB: 2-of-3   4.2 GB: 3-of-3
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licensecc-by-2.0
Context Length32764
Model Max Length32764
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Senku 70B Full 2.4bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 8bit1024K / 75 GB495
...B Instruct Gradient 1048K 4bit1024K / 39.7 GB493
...B Instruct Gradient 1048K 2bit1024K / 21.9 GB712
...0B Instruct Gradient 262K 4bit256K / 39.7 GB283
...0B Instruct Gradient 262K 8bit256K / 75 GB212
...0B Instruct Gradient 262K 2bit256K / 21.9 GB251
...t Gradient 262K 4.0bpw H6 EXL2256K / 37.2 GB351
... Gradient 262K 2.25bpw H6 EXL2256K / 22.2 GB110
...t Gradient 262K 3.5bpw H6 EXL2256K / 32.9 GB110
...t Gradient 262K 2.4bpw H6 EXL2256K / 23.5 GB90
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Senku-70B-Full-2.4bpw-h6-exl2.

Rank the Senku 70B Full 2.4bpw H6 EXL2 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 49482 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124