LLM EXPLORER 61,249 MODELS INDEXED

GeM2 Llamion 14B Base by vaiv

By vaiv · 8370 downloads
HF Repo ↗ Copy URL

GeM2 Llamion 14B Base is an open-source language model by vaiv. Features: 14b LLM, VRAM: 29GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.16.

  Arxiv:2605.25676   Conversational   Deploy:azure   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/vaiv/GeM2-Llamion-14B-Base 

GeM2 Llamion 14B Base Parameters and Internals

Model Type 
generative
Additional Notes 
Further technical specifications and study results will be detailed in an upcoming paper.
Training Details 
Methodology:
Transformed from Orion model into LLaMA architecture through parameter mapping and offline knowledge transfer.
Model Architecture:
LLaMA
LLM NameGeM2 Llamion 14B Base
Repository 🤗https://huggingface.co/vaiv/GeM2-Llamion-14B-Base 
Model Size14b
Required VRAM29 GB
Updated2026-05-27
Maintainervaiv
Model Typellama
Model Files  5.0 GB: 1-of-6   5.0 GB: 2-of-6   4.9 GB: 3-of-6   4.9 GB: 4-of-6   5.0 GB: 5-of-6   4.2 GB: 6-of-6
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.37.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|pad|>
Vocabulary Size84608
Torch Data Typebfloat16

Best Alternatives to GeM2 Llamion 14B Base

Best Alternatives
Context / RAM
Downloads
Likes
...struct 2512 Llamafied TextOnly256K / 27 GB93
...Qwen2.5llamaify 14B V23.3 200K195K / 29.7 GB105
...Qwen2.5llamaify 14B V23.1 200K195K / 29.7 GB151
GeM2 Llamion 14B LongChat195K / 29 GB79154
Openbuddy Zero 14B V22.3 32K32K / 28 GB84832
Phi4 14B R131K / 29.4 GB60
Rune 14B16K / 29.5 GB451
Rosemary 14B16K / 29.5 GB570
Sake 20B16K / 43.1 GB220
Loke 14B Sce16K / 29.5 GB01
Note: green Score (e.g. "73.2") means that the model is better than vaiv/GeM2-Llamion-14B-Base.