LLM EXPLORER 55,709 MODELS INDEXED

Diffusiongemma 26B A4B It 8bit by mlx-community

By mlx-community · 633 downloads
HF Repo ↗ Copy URL

Diffusiongemma 26B A4B It 8bit is an open-source language model by mlx-community. Features: 26b LLM, VRAM: 28GB, License: apache-2.0, Quantized.

  8-bit   8bit Base model:google/diffusiongem... Base model:quantized:google/di...   Conversational   Diffusion gemma   Image-text-to-text   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/diffusiongemma-26B-A4B-it-8bit 

Diffusiongemma 26B A4B It 8bit Parameters and Internals

LLM NameDiffusiongemma 26B A4B It 8bit
Repository 🤗https://huggingface.co/mlx-community/diffusiongemma-26B-A4B-it-8bit 
Base Model(s)  google/diffusiongemma-26B-A4B-it   google/diffusiongemma-26B-A4B-it
Model Size26b
Required VRAM28 GB
Updated2026-08-08
Maintainermlx-community
Model Typediffusion_gemma
Model Files  5.2 GB: 1-of-6   5.2 GB: 2-of-6   5.2 GB: 3-of-6   5.2 GB: 4-of-6   5.2 GB: 5-of-6   2.0 GB: 6-of-6
Quantization Type8bit
Model ArchitectureDiffusionGemmaForBlockDiffusion
Licenseapache-2.0
Transformers Version5.8.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Diffusiongemma 26B A4B It 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Diffusiongemma 26B A4B It 4bit0K / 16.6 GB227035
...iongemma 26B A4B It OptiQ 4bit0K / 16.7 GB197919
Diffusiongemma 26B A4B It 5bit0K / 19.4 GB1332
Diffusiongemma 26B A4B It 6bit0K / 22.3 GB2074
...iffusiongemma 26B A4B It NVFP40K / 18.8 GB1881298107
Diffusiongemma 26B A4B It0K / 51.6 GB102056
...iffusiongemma 26B A4B It Mxfp40K / 14.8 GB6166
...iffusiongemma 26B A4B It Nvfp40K / 15.6 GB2425
...iffusiongemma 26B A4B It Mxfp80K / 27.3 GB2103
Diffusiongemma 26B A4B It Bf160K / 51.6 GB1852
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/diffusiongemma-26B-A4B-it-8bit.