LLM EXPLORER 59,420 MODELS INDEXED

Chargen V2 8bpw EXL2 by Kooten

By Kooten · 1 downloads
HF Repo ↗ Copy URL

Chargen V2 8bpw EXL2 is an open-source language model by Kooten. Features: LLM, VRAM: 7.4GB, Context: 32K, License: cc-by-nc-4.0, Quantized, LLM Explorer Score: 0.11.

  Conversational   Endpoints compatible   Exl2   Mistral   Pytorch   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/Kooten/Chargen-v2-8bpw-exl2 

Chargen V2 8bpw EXL2 Parameters and Internals

Model Type 
Character generation
Additional Notes 
CharGen is designed to assist in creating characters for role-playing, utilizing a step-by-step dialogue format. Users are encouraged to read kubernetes-bad's own description and instructions for optimal use.
Input Output 
Input Format:
Dialogue format for character description.
Accepted Modalities:
text
Output Format:
Character description step-by-step
LLM NameChargen V2 8bpw EXL2
Repository 🤗https://huggingface.co/Kooten/Chargen-v2-8bpw-exl2 
Required VRAM7.4 GB
Updated2026-07-24
MaintainerKooten
Model Typemistral
Model Files  7.4 GB
Quantization Typeexl2
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-4.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32002
Torch Data Typefloat32

Best Alternatives to Chargen V2 8bpw EXL2

Best Alternatives
Context / RAM
Downloads
Likes
NemoMix Unleashed EXL2 4bpw1000K / 7.3 GB59
...al Small 2505 Unsloth Bnb 4bit128K / 15 GB825
...0.88 07.02 RP DPO Merged 16bit32K / 14.4 GB60
...eZephir Sft Instruct Ead 16bit32K / 14.4 GB560
...cr To Json V1 HQQ 1bit Smashed32K / 1.6 GB50
...cr To Json V1 HQQ 4bit Smashed32K / 4.2 GB50
ScikitLLM Model EXL232K / 3 GB51
...tral PairRM DPO 8.0bpw H8 EXL232K / 7.4 GB72
HamSter 0.2 8.0bpw H8 EXL232K / 7.4 GB31
...N L1 Chat RL V1.3.0bpw H6 EXL232K / 3 GB80
Note: green Score (e.g. "73.2") means that the model is better than Kooten/Chargen-v2-8bpw-exl2.