Gemma 4 31B It Mlx 4bit by Phipper

 »  All LLMs  »  Phipper  »  Gemma 4 31B It Mlx 4bit   URL Share it on

Gemma 4 31B It Mlx 4bit is an open-source language model by Phipper. Features: 31b LLM, VRAM: 18.5GB, License: gemma, Quantized, LLM Explorer Score: 0.33.

  4-bit   4bit Base model:google/gemma-4-31b-... Base model:quantized:google/ge...   Conversational   Gemma4   Google   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Gemma 4 31B It Mlx 4bit Benchmarks

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

Gemma 4 31B It Mlx 4bit Parameters and Internals

LLM NameGemma 4 31B It Mlx 4bit
Repository 🤗https://huggingface.co/Phipper/gemma-4-31b-it-mlx-4bit 
Base Model(s)  google/gemma-4-31B-it   google/gemma-4-31B-it
Model Size31b
Required VRAM18.5 GB
Updated2026-04-15
MaintainerPhipper
Model Typegemma4
Model Files  5.4 GB: 1-of-4   5.4 GB: 2-of-4   5.4 GB: 3-of-4   2.3 GB: 4-of-4
Quantization Type4bit
Model ArchitectureGemma4ForConditionalGeneration
Licensegemma
Transformers Version5.5.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Gemma 4 31B It Mlx 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 4 31B It PolarQuant Q50K / 21.4 GB9823
Gemma 4 31B IT NVFP40K / 32.6 GB675226360
Gemma 4 31B It0K / 62.6 GB4684513
Gemopus 4 31B It0K / 62.6 GB3836
Gemma 4 31B It Bf160K / 62.6 GB72254
Gemma4 Garnet 31B0K / 62.6 GB4979
Gemma 4 31B JANG 4M CRACK0K / 22.6 GB10892
...RD HERETIC UNCENSORED Thinking0K / 62.5 GB589913
...rnet 31B It Uncensored Heretic0K / 62.5 GB4523
Note: green Score (e.g. "73.2") means that the model is better than Phipper/gemma-4-31b-it-mlx-4bit.

Rank the Gemma 4 31B It Mlx 4bit Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52996 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a