What are the hardware requirements for Big Alice 28B V1?

Big Alice 28B V1 requires approximately 57.2 GB of VRAM and supports a context window of 64K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Big Alice 28B V1 and how large is it?

Big Alice 28B V1 is developed by TheDrummer, a model with 15b 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 Big Alice 28B V1?

Big Alice 28B V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Big Alice 28B V1 by TheDrummer — VRAM 57.2GB, 64K context

Name: Big Alice 28B V1
Author: TheDrummer

Big Alice 28B V1 is an open-source language model by TheDrummer. Features: 15b LLM, VRAM: 57.2GB, Context: 64K, License: mit, LLM Explorer Score: 0.18.

Base model:finetune:sillytilly... Base model:sillytilly/servicen... Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/TheDrummer/Big-Alice-28B-v1

Big Alice 28B V1 Parameters and Internals

LLM Name	Big Alice 28B V1
Repository 🤗	https://huggingface.co/TheDrummer/Big-Alice-28B-v1
Base Model(s)	...el Nemotron 15B Thinker Chatml SillyTilly/ServiceNow-AI-Apriel-Nemotron-15b-Thinker-Chatml
Model Size	15b
Required VRAM	57.2 GB
Updated	2026-08-01
Maintainer	TheDrummer
Model Type	mistral
Model Files	4.9 GB: 1-of-12 4.9 GB: 2-of-12 4.9 GB: 3-of-12 4.9 GB: 4-of-12 4.9 GB: 5-of-12 4.9 GB: 6-of-12 4.9 GB: 7-of-12 4.9 GB: 8-of-12 4.9 GB: 9-of-12 4.9 GB: 10-of-12 4.9 GB: 11-of-12 3.3 GB: 12-of-12
Model Architecture	MistralForCausalLM
License	mit
Context Length	65536
Model Max Length	65536
Transformers Version	4.51.3
Tokenizer Class	PreTrainedTokenizer
Padding Token	<pad>
Vocabulary Size	131072
Torch Data Type	bfloat16

Rank the Big Alice 28B V1 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 Big Alice 28B V1

Best Alternatives	Context / RAM	Downloads	Likes
Apriel Nemotron 15B Thinker	64K / 29.9 GB	665	127
Snowpiercer 15B V2	64K / 29.9 GB	6	12
Snowpiercer 15B V1	64K / 29.9 GB	15	26
Sol Reaver 15B Instruct	64K / 29.9 GB	17	15
...el Nemotron 15B Thinker Chatml	64K / 29.9 GB	8	10
Nemotron 15B Thinker Instruct	64K / 29.9 GB	10	0
Mistral 15B Instruct V0.1	32K / 28.4 GB	79	0

Note: green Score (e.g. "73.2") means that the model is better than TheDrummer/Big-Alice-28B-v1.