LLM EXPLORER 67,078 MODELS INDEXED

TranNhiem DeepCompression Gemma4 26B A4B It by trannhiem

By trannhiem · 121 downloads
HF Repo ↗ Copy URL

TranNhiem DeepCompression Gemma4 26B A4B It is an open-source language model by trannhiem. Features: 26b LLM, VRAM: 18GB, License: apache-2.0, LLM Explorer Score: 0.32.

  8-bit Base model:google/gemma-4-26b-... Base model:quantized:google/ge...   Compressed   Conversational   Endpoints compatible   Expert-pruning   Gemma4   Image-text-to-text   Mixture-of-experts   Modelopt   Nvfp4   Region:us   Safetensors   Sharded   Tensorflow   Vision   Vision-language   Vllm
Model Card on HF 🤗: https://huggingface.co/trannhiem/TranNhiem-DeepCompression-Gemma4-26B-A4B-it 

TranNhiem DeepCompression Gemma4 26B A4B It Parameters and Internals

LLM NameTranNhiem DeepCompression Gemma4 26B A4B It
Repository 🤗https://huggingface.co/trannhiem/TranNhiem-DeepCompression-Gemma4-26B-A4B-it 
Base Model(s)  Gemma 4 26B A4B It   google/gemma-4-26B-A4B-it
Model Size26b
Required VRAM18 GB
Updated2026-11-10
Maintainertrannhiem
Model Typegemma4
Model Files  10.0 GB: 1-of-2   8.0 GB: 2-of-2
Model ArchitectureGemma4ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.9.0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to TranNhiem DeepCompression Gemma4 26B A4B It

Best Alternatives
Context / RAM
Downloads
Likes
GEV 26B Decide0K / 51.6 GB10130222316
Gemma 4 26B A4B It0K / 51.6 GB104059891007
Gemma 4 26B A4B0K / 51.6 GB624397370
Gemma 4 26B A4B It0K / 51.6 GB2997229
Gemma 4 26B A4B StyleTune V20K / 53.1 GB159849
Gemma 4 26B A4B0K / 51.6 GB336819
Gemma 4 26B A4b It Bf160K / 51.6 GB15173
Gemma 4 26B A4B NVFP40K / 18.8 GB1424962126
Gemma 4 26B A4B It FP8 Dynamic0K / 28.6 GB113634938
Gemma 4 26B A4B It NVFP40K / 16.9 GB15466321
Note: green Score (e.g. "73.2") means that the model is better than trannhiem/TranNhiem-DeepCompression-Gemma4-26B-A4B-it.