LLM EXPLORER 58,297 MODELS INDEXED

Gemma 4 31B It UD MLX 4bit by unsloth

By unsloth · 792 downloads
HF Repo ↗ Copy URL

Gemma 4 31B It UD MLX 4bit is an open-source language model by unsloth. Features: 31b LLM, VRAM: 23.2GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.41, ELO: 1451.

  4-bit   4bit Base model:google/gemma-4-31b-... 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-4-31b-it-UD-MLX-4bit 

Gemma 4 31B It UD MLX 4bit Benchmarks

LMSys ELO 1451 vs 1272 (so35) 14.1%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Gemma 4 31B It UD MLX 4bit Parameters and Internals

LLM NameGemma 4 31B It UD MLX 4bit
Repository 🤗https://huggingface.co/unsloth/gemma-4-31b-it-UD-MLX-4bit 
Base Model(s)  Gemma 4 31B It   google/gemma-4-31B-it
Model Size31b
Required VRAM23.2 GB
Updated2026-08-10
Maintainerunsloth
Model Typegemma4
Model Files  5.3 GB: 1-of-5   5.4 GB: 2-of-5   5.3 GB: 3-of-5   5.3 GB: 4-of-5   1.9 GB: 5-of-5
Quantization Type4bit
Model ArchitectureGemma4ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.5.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Gemma 4 31B It UD MLX 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...emma 4 31B It Unsloth Bnb 4bit0K / 19.2 GB31317222
Gemma 4 31B It 4bit0K / 18.5 GB4506746
... 4 31B It Qat Q4 0 Unquantized0K / 62.6 GB997239
... 4 31B It Qat Q4 0 Unquantized0K / 62.6 GB20744
Gemma 4 31B It 8bit0K / 33.8 GB321417
Gemma 4 31B 8bit0K / 33.8 GB95724
Gemma 4 31B It MLX 8bit0K / 33.8 GB97215
Gemma 4 31B It 6bit0K / 26 GB9067
Gemma 4 31B It Qat W4a16 Ct0K / 23.3 GB218779555
Gemma 4 31B 4bit0K / 18.5 GB44811
Note: green Score (e.g. "73.2") means that the model is better than unsloth/gemma-4-31b-it-UD-MLX-4bit.