LLM EXPLORER 59,516 MODELS INDEXED

Gemma 4 31B It Assistant Bf16 by mlx-community

By mlx-community · 2975 downloads
HF Repo ↗ Copy URL

Gemma 4 31B It Assistant Bf16 is an open-source language model by mlx-community. Features: 31b LLM, VRAM: 0.9GB, License: gemma, LLM Explorer Score: 0.28.

Base model:finetune:google/gem... Base model:google/gemma-4-31b-...   Drafter   Gemma   Gemma4 assistant   Mlx   Mtp   Region:us   Safetensors   Speculative-decoding
Model Card on HF 🤗: https://huggingface.co/mlx-community/gemma-4-31B-it-assistant-bf16 

Gemma 4 31B It Assistant Bf16 Parameters and Internals

LLM NameGemma 4 31B It Assistant Bf16
Repository 🤗https://huggingface.co/mlx-community/gemma-4-31B-it-assistant-bf16 
Base Model(s)  Gemma 4 31B It Assistant   google/gemma-4-31B-it-assistant
Model Size31b
Required VRAM0.9 GB
Updated2026-07-03
Maintainermlx-community
Model Typegemma4_assistant
Model Files  0.9 GB
Model ArchitectureGemma4AssistantForCausalLM
Licensegemma
Transformers Version5.7.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Gemma 4 31B It Assistant Bf16

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 4 31B It Assistant0K / 0.9 GB1539849315
Gemma 4 31B It Assistant Fp80K / 0.8 GB1992
...Qat Q4 0 Unquantized Assistant0K / 0.9 GB2577822
...ma 4 31B It Qat Assistant Bf160K / 0.9 GB4951
...a 4 31B It Qat Assistant Mxfp80K / 0.5 GB2771
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/gemma-4-31B-it-assistant-bf16.