LLM EXPLORER 57,252 MODELS INDEXED

Custom KoLLM 13B V8 by PracticeLLM

By PracticeLLM · 11 downloads

Custom KoLLM 13B V8 is an open-source language model by PracticeLLM. Features: 13b LLM, VRAM: 26.4GB, Context: 2K, License: cc-by-nc-sa-4.0, LLM Explorer Score: 0.1.

Dataset:kyujinpy/openorca-ko-v...   Endpoints compatible   Ko   Llama   Pytorch   Region:us   Safetensors   Sharded   Tensorflow

Custom KoLLM 13B V8 Parameters and Internals

Model Type 
text generation
Supported Languages 
Korean (unknown)
Training Details 
Data Sources:
kyujinpy/OpenOrca-ko-v3
Model Architecture:
LLaMA2 transformer
LLM NameCustom KoLLM 13B V8
Repository πŸ€—https://huggingface.co/PracticeLLM/Custom-KoLLM-13B-v8 
Model Size13b
Required VRAM26.4 GB
Updated2026-08-01
MaintainerPracticeLLM
Model Typellama
Model Files  10.0 GB: 1-of-3   9.9 GB: 2-of-3   6.5 GB: 3-of-3   10.0 GB: 1-of-3   9.9 GB: 2-of-3   6.5 GB: 3-of-3
Supported Languagesko
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-sa-4.0
Context Length2048
Model Max Length2048
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size46336
Torch Data Typefloat16

Best Alternatives to Custom KoLLM 13B V8

Best Alternatives
Context / RAM
Downloads
Likes
Luminaura RP 13B128K / 26 GB91
Yarn Llama 2 13B 128K128K / 26 GB184113
Agent Llama2 13B 80K80K / 26.4 GB50
Chat Llama2 13B 80K80K / 52.8 GB50
LongAlign 13B 64K64K / 26 GB9613
LongAlign 13B 64K Base64K / 26 GB893
LongAlign 13B 64K64K / 26 GB1113
LongAlign 13B 64K Base64K / 26 GB63
Openbuddy Llama2 13B V15p1 64K64K / 26.1 GB44
Openbuddy Llama2 13b64k V1564K / 26.1 GB122
Note: green Score (e.g. "73.2") means that the model is better than PracticeLLM/Custom-KoLLM-13B-v8.