LLM EXPLORER 60,702 MODELS INDEXED

Gemma 4 26B A4B It Qat Assistant Mxfp8 by mlx-community

By mlx-community · 216 downloads
HF Repo ↗ Copy URL

Gemma 4 26B A4B It Qat Assistant Mxfp8 is an open-source language model by mlx-community. Features: 26b LLM, VRAM: 0.4GB, License: gemma, Quantized, LLM Explorer Score: 0.25.

  8-bit Base model:google/gemma-4-26b-... Base model:quantized:google/ge...   Conversational   Draft-model   En   Gemma   Gemma-4   Gemma-4-26b-a4b   Gemma4 assistant   Mlx   Mlx-vlm   Mtp   Mxfp8   Q4   Q4 0   Quantized   Region:us   Safetensors   Speculative-decoding
Model Card on HF 🤗: https://huggingface.co/mlx-community/gemma-4-26B-A4B-it-qat-assistant-mxfp8 

Gemma 4 26B A4B It Qat Assistant Mxfp8 Parameters and Internals

LLM NameGemma 4 26B A4B It Qat Assistant Mxfp8
Repository 🤗https://huggingface.co/mlx-community/gemma-4-26B-A4B-it-qat-assistant-mxfp8 
Base Model(s)  ...Qat Q4 0 Unquantized Assistant   google/gemma-4-26B-A4B-it-qat-q4_0-unquantized-assistant
Model Size26b
Required VRAM0.4 GB
Updated2026-08-10
Maintainermlx-community
Model Typegemma4_assistant
Model Files  0.4 GB
Supported Languagesen
Quantization Typeq4|q4_0
Model ArchitectureGemma4AssistantForCausalLM
Licensegemma
Transformers Version5.10.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Gemma 4 26B A4B It Qat Assistant Mxfp8

Best Alternatives
Context / RAM
Downloads
Likes
...Qat Q4 0 Unquantized Assistant0K / 0.8 GB1207416
... 26B A4B It Qat Assistant 4bit0K / 0.2 GB8431
... 26B A4B It Qat Assistant Bf160K / 0.8 GB2851
...26B A4B It Qat Assistant Mxfp40K / 0.2 GB2171
Gemma 4 26B A4B It Assistant0K / 0.8 GB273959169
...ma 4 26B A4B It Assistant Bf160K / 0.8 GB190921
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/gemma-4-26B-A4B-it-qat-assistant-mxfp8.