LLM EXPLORER 61,561 MODELS INDEXED

Smut Llama 8B Smutromance 32K Peft by jspr

By jspr · 0 downloads

Smut Llama 8B Smutromance 32K Peft is an open-source language model by jspr. Features: 8b LLM, VRAM: 0.3GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.12.

  4bit Base model:finetune:unsloth/ll... Base model:unsloth/llama-3-8b-...   En   Endpoints compatible   Llama   Lora   Quantized   Region:us   Safetensors   Trl   Unsloth

Smut Llama 8B Smutromance 32K Peft Parameters and Internals

LLM NameSmut Llama 8b Smutromance 32k Peft
Repository πŸ€—https://huggingface.co/jspr/smut_llama_8b_smutromance_32k_peft 
Base Model(s)  Llama 3 8B Bnb 4bit   unsloth/llama-3-8b-bnb-4bit
Model Size8b
Required VRAM0.3 GB
Updated2026-08-08
Maintainerjspr
Model Files  0.3 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureAutoModel
Licenseapache-2.0
Is Biasednone
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesk_proj|v_proj|down_proj|gate_proj|q_proj|up_proj|o_proj
LoRA Alpha16
LoRA Dropout0
R Param32

Best Alternatives to Smut Llama 8B Smutromance 32K Peft

Best Alternatives
Context / RAM
Downloads
Likes
My Custom Llm0K / 0.2 GB181
Novashop Support Lora0K / 0.2 GB91
Xino Adapter0K / 0.2 GB240
Torki Lora0K / 0 GB50
Llama3.1 8B Reflection Lora0K / 0.3 GB01
...a 3 8B Bnb 4bit Robot Instruct0K / 0.2 GB80
Llama 3 Instruct LiPPA LoRA 8B0K / 2.7 GB60
...lama 3 LimaRP Instruct LoRA 8B0K / 2.7 GB50
Educate Ai0K / 0.2 GB50
Lora Model0K / 0.7 GB01
Note: green Score (e.g. "73.2") means that the model is better than jspr/smut_llama_8b_smutromance_32k_peft.