Psyonic Cetacean 20B V2.4.0bpw H6 EXL2 by ToastyPigeon

 ยป  All LLMs  ยป  ToastyPigeon  ยป  Psyonic Cetacean 20B V2.4.0bpw H6 EXL2   URL Share it on

Psyonic Cetacean 20B V2.4.0bpw H6 EXL2 is an open-source language model by ToastyPigeon. Features: 20b LLM, VRAM: 10.3GB, Context: 4K, Quantized, LLM Explorer Score: 0.12.

  Arxiv:2203.05482   4-bit   Endpoints compatible   Exl2   Llama   Merge   Mergekit   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Psyonic Cetacean 20B V2.4.0bpw 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").
Psyonic Cetacean 20B V2.4.0bpw H6 EXL2 (ToastyPigeon/psyonic-cetacean-20b-v2-4.0bpw-h6-exl2)
๐ŸŒŸ Advertise your project ๐Ÿš€

Psyonic Cetacean 20B V2.4.0bpw H6 EXL2 Parameters and Internals

LLM NamePsyonic Cetacean 20B V2.4.0bpw H6 EXL2
Repository ๐Ÿค—https://huggingface.co/ToastyPigeon/psyonic-cetacean-20b-v2-4.0bpw-h6-exl2 
Model Size20b
Required VRAM10.3 GB
Updated2026-01-28
MaintainerToastyPigeon
Model Typellama
Model Files  8.6 GB: 1-of-2   1.7 GB: 2-of-2
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.36.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Psyonic Cetacean 20B V2.4.0bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
InternLM2 Chat 20B ToxicRP32K / 39.9 GB60
...a Quality Float32 4 25bpw EXL24K / 10.9 GB22
...ra Quality Float32 8 0bpw EXL24K / 17.5 GB31
...ra Quality Float32 5 0bpw EXL24K / 12.8 GB50
... Unquirked 20B 4.25bpw H8 EXL24K / 11 GB31
...a No Robots 20B 3.0bpw H6 EXL24K / 7.8 GB41
DaringMaid 20B V1.1 4bpw EXL24K / 10.4 GB22
DaringMaid 20B V1.1 3bpw EXL24K / 7.9 GB41
DaringMaid 20B 3bpw EXL24K / 7.9 GB91
DaringMaid 20B 6bpw EXL24K / 15.3 GB42
Note: green Score (e.g. "73.2") means that the model is better than ToastyPigeon/psyonic-cetacean-20b-v2-4.0bpw-h6-exl2.

Rank the Psyonic Cetacean 20B V2.4.0bpw 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? 52721 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum โ€” our secure, self-hosted AI agent for server management.
Release v20260328a