LLM EXPLORER 59,420 MODELS INDEXED

Llewd 8B 64K by fimbulvntr

By fimbulvntr · 8 downloads
HF Repo ↗ Copy URL

Llewd 8B 64K is an open-source language model by fimbulvntr. Features: 8b LLM, VRAM: 0.3GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.13.

Base model:quantized:unsloth/l...   Base model:unsloth/llama-3-8b   En   Endpoints compatible   Gguf   Llama   Lora   Quantized   Region:us   Safetensors   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/fimbulvntr/llewd-8b-64k 

Llewd 8B 64K Parameters and Internals

Model Type 
text-generation-inference, transformers, unsloth, llama, trl
Additional Notes 
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
LLM NameLlewd 8B 64K
Repository 🤗https://huggingface.co/fimbulvntr/llewd-8b-64k 
Base Model(s)  Llama 3 8B   unsloth/llama-3-8b
Model Size8b
Required VRAM0.3 GB
Updated2025-09-23
Maintainerfimbulvntr
Model Files  0.3 GB   16.1 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModel
Licenseapache-2.0
Is Biasednone
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|q_proj|o_proj|down_proj|k_proj|gate_proj|up_proj
LoRA Alpha64
LoRA Dropout0
R Param32

Best Alternatives to Llewd 8B 64K

Best Alternatives
Context / RAM
Downloads
Likes
...lama 3.1 8B Roleplay BSNL Gguf0K / 4.9 GB97311
...ma 3.1 8B Roleplay Airtel Gguf0K / 4.9 GB6588
Llama 3.1 8B Roleplay Jio Gguf0K / 4.9 GB1235
Llama 3.1 8B Rp Tadashinu Gguf0K / 4.9 GB577
Llama 3.1 8B OneLastStory Gguf0K / 4.9 GB435
...B Instruct Bnb 4bit 24 1 100 10K / 16.1 GB590
CleverBoi Llama 3.1 8B V20K / 16.1 GB8000
...leverBoi Llama 3.1 8B Instruct0K / 0.2 GB8661
Meta Llama 3 8B Instruct GGUF0K / 2 GB96368103
...ma 3 8B Instruct 32K V0.1 GGUF0K / 2 GB8108759
Note: green Score (e.g. "73.2") means that the model is better than fimbulvntr/llewd-8b-64k.