LLM EXPLORER 59,420 MODELS INDEXED

Gemma 4 12B It Qat Assistant 4bit by mlx-community

By mlx-community · 1536 downloads
HF Repo ↗ Copy URL

Gemma 4 12B It Qat Assistant 4bit is an open-source language model by mlx-community. Features: 12b LLM, VRAM: 0.2GB, License: gemma, Quantized, LLM Explorer Score: 0.28.

  4-bit   4bit Base model:google/gemma-4-12b-... Base model:quantized:google/ge...   Conversational   Draft-model   En   Gemma   Gemma-4   Gemma-4-12b   Gemma4 unified assistant   Mlx   Mlx-vlm   Mtp   Q4   Q4 0   Quantized   Region:us   Safetensors   Speculative-decoding
Model Card on HF 🤗: https://huggingface.co/mlx-community/gemma-4-12B-it-qat-assistant-4bit 

Gemma 4 12B It Qat Assistant 4bit Parameters and Internals

LLM NameGemma 4 12B It Qat Assistant 4bit
Repository 🤗https://huggingface.co/mlx-community/gemma-4-12B-it-qat-assistant-4bit 
Base Model(s)  ...Qat Q4 0 Unquantized Assistant   google/gemma-4-12B-it-qat-q4_0-unquantized-assistant
Model Size12b
Required VRAM0.2 GB
Updated2026-08-05
Maintainermlx-community
Model Typegemma4_unified_assistant
Model Files  0.2 GB
Supported Languagesen
Quantization Typeq4|q4_0|4bit
Model ArchitectureGemma4UnifiedAssistantForCausalLM
Licensegemma
Transformers Version5.10.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Gemma 4 12B It Qat Assistant 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...Qat Q4 0 Unquantized Assistant0K / 0.8 GB9428020
Gemma 4 12B It Assistant0K / 0.8 GB114604103
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/gemma-4-12B-it-qat-assistant-4bit.