LLM EXPLORER 63,069 MODELS INDEXED

Ael Coder 16B MoE by Prannesshkva

By Prannesshkva · 1349 downloads
HF Repo ↗ Copy URL

Ael Coder 16B MoE is an open-source language model by Prannesshkva. Features: 15.7b LLM, VRAM: 31.4GB, Context: 160K, License: cc-by-nc-nd-4.0, MoE, Instruction-Based, Code Generating, LLM Explorer Score: 0.31.

  Ael   Ael-coder   Ael-coder-16b-moe Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a...   Bounded-memory   Code-generation   Codegen   Conversational   Custom code   En   Instruct   Isom   Isom-r2   Isom deepseek coder v2   Long-context   Mixture-of-experts   Moe   Region:us   Repo-level   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/Prannesshkva/Ael-Coder-16B-MoE 

Ael Coder 16B MoE Parameters and Internals

LLM NameAel Coder 16B MoE
Repository 🤗https://huggingface.co/Prannesshkva/Ael-Coder-16B-MoE 
Base Model(s)  ...eepSeek Coder V2 Lite Instruct   deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
Model Size15.7b
Required VRAM31.4 GB
Updated2026-10-05
MaintainerPrannesshkva
Model Typeisom_deepseek_coder_v2
Instruction-BasedYes
Model Files  8.6 GB: 1-of-4   8.6 GB: 2-of-4   8.6 GB: 3-of-4   5.6 GB: 4-of-4
Supported Languagesen zh
Generates CodeYes
Model ArchitectureAelCoder16BMoEForCausalLM|ISOMR2Coder16BMoEForCausalLM|ISOMR1Coder16BMoEForCausalLM|IsomDeepseekCoderV2ForCausalLM
Licensecc-by-nc-nd-4.0
Context Length163840
Model Max Length163840
Transformers Version4.39.3
Tokenizer ClassPreTrainedTokenizerFast
Beginning of Sentence Token<｜begin▁of▁sentence｜>
End of Sentence Token<｜end▁of▁sentence｜>
Vocabulary Size102400
Torch Data Typebfloat16