LLM EXPLORER 56,604 MODELS INDEXED

G4 Dark Soul 26B A4B Mlx 8Bit by McG-221

By McG-221 · 132 downloads
HF Repo ↗ Copy URL

G4 Dark Soul 26B A4B Mlx 8Bit is an open-source language model by McG-221. Features: 26b LLM, VRAM: 26.8GB, License: apache-2.0, Quantized.

  8-bit   8bit Base model:quantized:vortex5/g... Base model:vortex5/g4-dark-sou...   Conversational   Endpoints compatible   Gemma4   Image-text-to-text   Merge   Mergekit   Mlx   Mlx-my-repo   Quantized   Region:us   Roleplay   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/McG-221/G4-Dark-Soul-26B-A4B-mlx-8Bit 

G4 Dark Soul 26B A4B Mlx 8Bit Parameters and Internals

LLM NameG4 Dark Soul 26B A4B Mlx 8Bit
Repository 🤗https://huggingface.co/McG-221/G4-Dark-Soul-26B-A4B-mlx-8Bit 
Base Model(s)  G4 Dark Soul 26B A4B   Vortex5/G4-Dark-Soul-26B-A4B
Model Size26b
Required VRAM26.8 GB
Updated2026-08-09
MaintainerMcG-221
Model Typegemma4
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   0.8 GB: 6-of-6
Quantization Type8bit
Model ArchitectureGemma4ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.5.3
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to G4 Dark Soul 26B A4B Mlx 8Bit

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 4 26B A4b It 4bit0K / 15.4 GB2754379
...6B A4B It Qat Q4 0 Unquantized0K / 51.6 GB34873
Gemma 4 26B A4b It 8bit0K / 27.9 GB291714
Gemma 4 26B A4b 4bit0K / 15.6 GB48819
Gemma 4 26B A4b It 6bit0K / 21.7 GB6117
Gemma 4 26B A4b 8bit0K / 27.9 GB1627
Gemma 4 26B A4b It 5bit0K / 18.5 GB1113
Gemma 4 26B A4b 6bit0K / 21.7 GB603
Gemma 4 26B A4b 5bit0K / 18.7 GB451
...ma 4 26B A4B It Qat OptiQ 4bit0K / 20.7 GB26744
Note: green Score (e.g. "73.2") means that the model is better than McG-221/G4-Dark-Soul-26B-A4B-mlx-8Bit.