LLM EXPLORER 61,561 MODELS INDEXED

L3 Nymeria 8B by tannedbum

By tannedbum · 13 downloads
HF Repo ↗ Copy URL

L3 Nymeria 8B is an open-source language model by tannedbum. Features: 8b LLM, VRAM: 16GB, Context: 8K, License: cc-by-nc-4.0, Instruction-Based, Merged, LLM Explorer Score: 0.13.

  Merged Model   Autotrain compatible Base model:princeton-nlp/llama... Base model:sao10k/l3-8b-stheno...   Conversational   En   Endpoints compatible   Instruct   Llama   Llama3   Not-for-all-audiences   Region:us   Roleplay   Safetensors   Sharded   Sillytavern   Tensorflow
Model Card on HF 🤗: https://huggingface.co/tannedbum/L3-Nymeria-8B 

L3 Nymeria 8B Parameters and Internals

Model Type 
text generation, roleplay, merge, sillytavern
Use Cases 
Areas:
research, roleplay
Additional Notes 
This model is the result of a balanced merge using the slerp method, designed for high-end roleplay purposes with a mix of realism and roleplay strength.
Supported Languages 
en (English)
Training Details 
Data Sources:
Gryphe/Opus-WritingPrompts, Roleplaying Samples from c2 Logs
Methodology:
Manual filtering and merging using slerp method, hyperparameter tuning
Model Architecture:
Merged model architecture from Stheno-v3.2 and Llama-3-SimPO
Input Output 
Input Format:
Text Prompt
Accepted Modalities:
text
Output Format:
Text Completion
Release Notes 
Version:
v3.2
Notes:
Mix of SFW and NSFW storywriting data, improved instruction adherence, better multi-turn coherency, manual filtering for quality.
LLM NameL3 Nymeria 8B
Repository 🤗https://huggingface.co/tannedbum/L3-Nymeria-8B 
Base Model(s)  Llama 3 Instruct 8B SimPO   Sao10K/L3-8B-Stheno-v3.2   princeton-nlp/Llama-3-Instruct-8B-SimPO   Sao10K/L3-8B-Stheno-v3.2
Merged ModelYes
Model Size8b
Required VRAM16 GB
Updated2025-10-28
Maintainertannedbum
Model Typellama
Instruction-BasedYes
Model Files  3.0 GB: 1-of-6   3.0 GB: 2-of-6   2.9 GB: 3-of-6   2.9 GB: 4-of-6   2.9 GB: 5-of-6   1.3 GB: 6-of-6
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length8192
Model Max Length8192
Transformers Version4.41.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Quantized Models of the L3 Nymeria 8B

Model
Likes
Downloads
VRAM
L3 Nymeria 8B GGUF3120 GB

Best Alternatives to L3 Nymeria 8B

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB1135125
UltraLong Thinking4192K / 16.1 GB23
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB12418
Cthulhu 8B V1.41048K / 16.1 GB1010
...raLong 1M Instruct Abliterated1048K / 32.1 GB49
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB70259
Zero Llama 3.1 8B Beta61048K / 16.1 GB71
Note: green Score (e.g. "73.2") means that the model is better than tannedbum/L3-Nymeria-8B.