What are the hardware requirements for Boulesis V2.1 26B A4B 8bit?

Boulesis V2.1 26B A4B 8bit requires approximately 27.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Boulesis V2.1 26B A4B 8bit and how large is it?

Boulesis V2.1 26B A4B 8bit is developed by McG-221, a model with 26b 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 Boulesis V2.1 26B A4B 8bit?

Boulesis V2.1 26B A4B 8bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Boulesis V2.1 26B A4B 8bit by McG-221 — VRAM 27.6GB

Name: Boulesis V2.1 26B A4B 8bit
Author: McG-221

Boulesis V2.1 26B A4B 8bit is an open-source language model by McG-221. Features: 26b LLM, VRAM: 27.6GB, Quantized, LLM Explorer Score: 0.31.

8-bit 8bit Base model:quantized:submaroon... Base model:submaroon/boulesis-... Conversational En Gemma4 Mlx Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/McG-221/Boulesis-v2.1-26B-A4B-8bit

Boulesis V2.1 26B A4B 8bit Parameters and Internals

LLM Name	Boulesis V2.1 26B A4B 8bit
Repository 🤗	https://huggingface.co/McG-221/Boulesis-v2.1-26B-A4B-8bit
Base Model(s)	SubMaroon/Boulesis-v2.1-26B-A4B SubMaroon/Boulesis-v2.1-26B-A4B
Model Size	26b
Required VRAM	27.6 GB
Updated	2026-09-16
Maintainer	McG-221
Model Type	gemma4
Model Files	5.2 GB: 1-of-6 5.2 GB: 2-of-6 5.2 GB: 3-of-6 5.2 GB: 4-of-6 5.2 GB: 5-of-6 1.6 GB: 6-of-6
Supported Languages	en
Quantization Type	8bit
Model Architecture	Gemma4ForConditionalGeneration
Model Max Length	262144
Transformers Version	5.17.0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the Boulesis V2.1 26B A4B 8bit 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 Boulesis V2.1 26B A4B 8bit

Best Alternatives	Context / RAM	Downloads	Likes
...6B A4B It Qat Q4 0 Unquantized	0K / 51.6 GB	33696	50
Gemma 4 26B A4b It 4bit	0K / 15.4 GB	27543	79
...6B A4B It Qat Q4 0 Unquantized	0K / 51.6 GB	3487	3
Gemma 4 26B A4b It 8bit	0K / 27.9 GB	2917	14
Gemma 4 26B A4b It UD MLX 4bit	0K / 16.2 GB	1527	34
Gemma 4 26B A4b It MLX 8bit	0K / 27.9 GB	936	16
...at Q4 0 Unquantized Heretic Ja	0K / 51.6 GB	34	1
Gemma 4 26B A4b 4bit	0K / 15.6 GB	488	19
Gemma 4 26B A4b It 6bit	0K / 21.7 GB	611	7
Gemma 4 26B A4b It UD MLX 3bit	0K / 13.1 GB	455	8

Note: green Score (e.g. "73.2") means that the model is better than McG-221/Boulesis-v2.1-26B-A4B-8bit.