LLM EXPLORER 56,604 MODELS INDEXED

Gemma 4 26B A4b It 4bit by mlx-community

By mlx-community · 27543 downloads
HF Repo ↗ Copy URL

Gemma 4 26B A4b It 4bit is an open-source language model by mlx-community. Features: 26b LLM, VRAM: 15.4GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.47, ELO: 1438.

  4-bit   4bit Base model:google/gemma-4-26b-... Base model:quantized:google/ge...   Conversational   Gemma4   Image-text-to-text   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/gemma-4-26b-a4b-it-4bit 

Gemma 4 26B A4b It 4bit 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 4bit Parameters and Internals

LLM NameGemma 4 26B A4b It 4bit
Repository 🤗https://huggingface.co/mlx-community/gemma-4-26b-a4b-it-4bit 
Base Model(s)  Gemma 4 26B A4B It   google/gemma-4-26B-A4B-it
Model Size26b
Required VRAM15.4 GB
Updated2026-07-26
Maintainermlx-community
Model Typegemma4
Model Files  5.3 GB: 1-of-3   5.4 GB: 2-of-3   4.7 GB: 3-of-3
Quantization Type4bit
Model ArchitectureGemma4ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.5.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Gemma 4 26B A4b It 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...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
Gemma 4 26B A4B It Qat 4bit0K / 15.6 GB23494