LLM EXPLORER 59,516 MODELS INDEXED

LunarAI by ThePegasusGroup

By ThePegasusGroup · 24 downloads
HF Repo ↗ Copy URL

LunarAI is an open-source language model by ThePegasusGroup. Features: 15.7b LLM, VRAM: 31.4GB, Context: 160K, License: apache-2.0, Quantized, LLM Explorer Score: 0.19.

  Code-generation   Conversational   Custom code   Dataset:custom spigot dataset   Deepseek-coder   Deepseek v2   Endpoints compatible   Finetuned   Gguf   Instruct   Minecraft   Ollama   Quantized   Region:us   Safetensors   Sharded   Spigot   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ThePegasusGroup/LunarAI 

LunarAI Parameters and Internals

LLM NameLunarAI
Repository 🤗https://huggingface.co/ThePegasusGroup/LunarAI 
Model Size15.7b
Required VRAM31.4 GB
Updated2026-08-05
MaintainerThePegasusGroup
Model Typedeepseek_v2
Model Files  16.7 GB   5.0 GB: 1-of-7   5.0 GB: 2-of-7   5.0 GB: 3-of-7   5.0 GB: 4-of-7   5.0 GB: 5-of-7   5.0 GB: 6-of-7   1.4 GB: 7-of-7
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureDeepseekV2ForCausalLM
Licenseapache-2.0
Context Length163840
Model Max Length163840
Transformers Version4.53.3
Tokenizer ClassLlamaTokenizerFast
Padding Token<｜end▁of▁sentence｜>
Vocabulary Size102400
Torch Data Typebfloat16

Best Alternatives to LunarAI

Best Alternatives
Context / RAM
Downloads
Likes
...eepSeek Coder V2 Lite Instruct160K / 31.4 GB542062628
...eek Coder V2 Lite Instruct AWQ160K / 9.1 GB785311
DeepSeek V2 Lite Chat160K / 31.4 GB1354449144
DeepSeek V2 Lite160K / 31.4 GB494498183
...e Sft Math7k 1epoch 1e 4 Gamma160K / 31.4 GB111
Dsv2 Lite Coder Codeio Pp160K / 31.4 GB22
DeepSeek Coder V2 Lite Base160K / 31.4 GB5350114
KwaiCoder DS V2 Lite Base160K / 31.4 GB377
...eepSeek Coder V2 Lite Base AWQ160K / 9.1 GB1614
...2 Lite Instruct FlashAttnPatch160K / 31.4 GB240
Note: green Score (e.g. "73.2") means that the model is better than ThePegasusGroup/LunarAI.