Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · zerofata

L3.3-GeneticLemonade-Opus-70B

L3.3-GeneticLemonade-Opus-70B is a 70.55B-parameter Llama text-generation merge from zerofata. Its model card documents a three-model RP merge with an sce configuration.

Publisher
zerofata
Task
text-generation
Model type
llama
License
llama3
Library
transformers
Publication status
Accepted · not indexed

Model overview

L3.3-GeneticLemonade-Opus-70B is published by zerofata as a llama-based text-generation merge. The captured configuration identifies LlamaForCausalLM and Safetensors metadata reports 70553706496 parameters. According to the model card, it combines three RP models with mergekit relationships recorded in the hub tags.

Recorded capabilities

Documented three-model merge

According to the model card and hub tags, the release merges zerofata/L3.3-GeneticLemonade-Unleashed-v3-70B, Delta-Vector/Plesio-70B, and TheDrummer/Anubis-70B-v1.1 on a shisa-ai/shisa-v2-llama3.3-70b base with the sce method.

RP and ERP positioning

According to the model card, GeneticLemonade-Unleashed-v3 is described as a creative generalist RP/ERP model, while Plesio-70B is described as a unique prose and dialogue RP/ERP model.

Noted quant variants

According to the model card, GGUF iMatrix and EXL3 4.25bpw quant variants are listed alongside the bfloat16 merge output.

Llama 70.55B Transformers record

Captured config identifies LlamaForCausalLM and llama, with Safetensors metadata reporting 70553706496 parameters and transformers library support.

Llama3 record

Card data records llama3, with hub tags confirming license llama3.

Use cases in the source record

  • Conversational roleplay text generation using the captured transformers Llama merge with inference-endpoint compatibility.
  • Merge experiments referencing the documented three-source sce configuration and the listed GGUF and EXL3 quant variants.

Limitations and unknowns

  • No evaluation results were extracted from this record.
  • No context-window value was extracted from this record.
  • Provider state is historical snapshot data, not independently refreshed current availability.
  • Roleplay quality characterizations such as solid, stable, creative, and unique prose are publisher descriptions and were not independently verified by Ethen.

Source and provenance

Source: zerofata/L3.3-GeneticLemonade-Opus-70B

Captured: Unknown. Processed: 2026-09-07T19:36:04.336584+00:00.

GENETIC LEMONADE Opus 01 // OVERVIEW Felt like making a merge. This model combines three individually solid, stable and distinctly different RP models. zerofata/GeneticLemonade-Unleashed-v3 Creative, generalist RP / ERP model. Delta-Vector/Plesio-70B Unique prose and unique dialogue RP / ERP model. TheDrummer/Anubis-70B-v1.1 Character portrayal, neutrally aligned RP / ERP model. 02 // SILLYTAVERN SETTINGS Play with these, they are not the 'best' settings just a stable baseline. Recommended Samplers > Temp: 0.9 - 1.2 > MinP: 0.03 - 0.04 > TopP: 0.9 - 1.0 > Dry: 0.8, 1.75, 4 Instruct Llama-3-Instruct-Names but you will need to uncheck…

F001F002F003F004F005F006F007F008F009F010F011F012F013F014F015