What are the hardware requirements for Basal Omni 1.0 Ultra?

Basal Omni 1.0 Ultra requires approximately 62.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Basal Omni 1.0 Ultra and how large is it?

Basal Omni 1.0 Ultra is developed by Remek, a model with 31b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Basal Omni 1.0 Ultra?

Basal Omni 1.0 Ultra is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Basal Omni 1.0 Ultra by Remek — VRAM 62.5GB

Name: Basal Omni 1.0 Ultra
Author: Remek

Basal Omni 1.0 Ultra is an open-source language model by Remek. Features: 31b LLM, VRAM: 62.5GB, License: apache-2.0, LLM Explorer Score: 0.38.

Base model:finetune:google/gem... Base model:google/gemma-4-31b-... Calibration Classification Conversational Decision-making En Endpoints compatible Experimental Gemma4 Image-text-to-text Pl Polish Region:us Safetensors Sharded Tensorflow Typed-decisions

Model Card on HF 🤗: https://huggingface.co/Remek/basal-omni-1.0-ultra

Basal Omni 1.0 Ultra Parameters and Internals

LLM Name	Basal Omni 1.0 Ultra
Repository 🤗	https://huggingface.co/Remek/basal-omni-1.0-ultra
Base Model(s)	Gemma 4 31B It google/gemma-4-31B-it
Model Size	31b
Required VRAM	62.5 GB
Updated	2026-10-21
Maintainer	Remek
Model Type	gemma4
Model Files	49.9 GB: 1-of-2 12.6 GB: 2-of-2
Supported Languages	pl en
Model Architecture	Gemma4ForConditionalGeneration
License	apache-2.0
Transformers Version	5.17.0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the Basal Omni 1.0 Ultra capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to Basal Omni 1.0 Ultra

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 4 31B It	0K / 62.6 GB	10706625	2780
Gemma 4 31B It	0K / 62.6 GB	30339	22
Gemma 4 31B IT NVFP4	0K / 32.6 GB	2773900	547
Gemma 4 31B	0K / 62.6 GB	1785	19
Gemma 4 31B JANG 4M CRACK	0K / 22.6 GB	24056	1704
Gemma 4 31B	0K / 62.6 GB	694395	498
Gemma 4 31B It FP8 Block	0K / 33.3 GB	3798582	44
Gemma 4 31B It NVFP4	0K / 23.3 GB	1115539	57
Quyet 1.0 Large	0K / 62.6 GB	1128	42
Gemma 4 31B It Abliterated	0K / 62.5 GB	751355	24

Note: green Score (e.g. "73.2") means that the model is better than Remek/basal-omni-1.0-ultra.