LLM EXPLORER 58,297 MODELS INDEXED

Gemma 4 26B A4b It UD MLX 3bit by unsloth

By unsloth · 455 downloads
HF Repo ↗ Copy URL

Gemma 4 26B A4b It UD MLX 3bit is an open-source language model by unsloth. Features: 26b LLM, VRAM: 13.1GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.4, ELO: 1438.

  3-bit   3bit Base model:google/gemma-4-26b-... Base model:quantized:google/ge...   Conversational   Gemma   Gemma4   Google   Image-text-to-text   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/gemma-4-26b-a4b-it-UD-MLX-3bit 

Gemma 4 26B A4b It UD MLX 3bit Benchmarks

LMSys ELO 1438 vs 1272 (so35) 13.1%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Gemma 4 26B A4b It UD MLX 3bit Parameters and Internals

LLM NameGemma 4 26B A4b It UD MLX 3bit
Repository 🤗https://huggingface.co/unsloth/gemma-4-26b-a4b-it-UD-MLX-3bit 
Base Model(s)  Gemma 4 26B A4B It   google/gemma-4-26B-A4B-it
Model Size26b
Required VRAM13.1 GB
Updated2026-08-10
Maintainerunsloth
Model Typegemma4
Model Files  5.3 GB: 1-of-3   5.3 GB: 2-of-3   2.5 GB: 3-of-3
Quantization Type3bit
Model ArchitectureGemma4ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.5.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Gemma 4 26B A4b It UD MLX 3bit

Best Alternatives
Context / RAM
Downloads
Likes
...6B A4B It Qat Q4 0 Unquantized0K / 51.6 GB3369650
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 It UD MLX 4bit0K / 16.2 GB152734
...at Q4 0 Unquantized Heretic Ja0K / 51.6 GB341
Gemma 4 26B A4b It MLX 8bit0K / 27.9 GB93616
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
Note: green Score (e.g. "73.2") means that the model is better than unsloth/gemma-4-26b-a4b-it-UD-MLX-3bit.