What are the hardware requirements for BADMISTRAL 1.5B?

BADMISTRAL 1.5B requires approximately 3.1 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed BADMISTRAL 1.5B and how large is it?

BADMISTRAL 1.5B is developed by UnfilteredAI, a model with 1.5b 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 BADMISTRAL 1.5B?

BADMISTRAL 1.5B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

BADMISTRAL 1.5B by UnfilteredAI — VRAM 3.1GB, 8K context

Name: BADMISTRAL 1.5B
Author: UnfilteredAI

BADMISTRAL 1.5B is an open-source language model by UnfilteredAI. Features: 1.5b LLM, VRAM: 3.1GB, Context: 8K, License: apache-2.0, LLM Explorer Score: 0.15.

Autotrain compatible Base model:finetune:oevortex/b... Base model:oevortex/babymistra... Conversational En Endpoints compatible Mistral Not-for-all-audiences Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/UnfilteredAI/BADMISTRAL-1.5B

BADMISTRAL 1.5B Parameters and Internals

Model Type

text-generation

Use Cases

Areas:

research, exploratory purposes

Applications:

creative writing, dialogue systems

Primary Use Cases:

exploring 'dark' or boundary-pushing topics

Limitations:

not appropriate for certain tasks or audiences, lack of real-time knowledge, bias and hallucinations

Considerations:

Use cautiously and ensure proper review of generated content.

Additional Notes

BADMISTRAL-1.5B provides unrestricted output, avoiding traditional ethical boundaries and content filters.

Supported Languages

en (Proficient)

Training Details

Data Volume:

1.5 trillion tokens

Training Time:

70 days

Hardware Used:

4x NVIDIA A100 GPUs

Model Architecture:

Mistral-based

Responsible Ai Considerations

Fairness:

Like all models, it may reflect biases present in its training data.

Transparency:

No Moral or Safety Constraints

LLM Name	BADMISTRAL 1.5B
Repository 🤗	https://huggingface.co/UnfilteredAI/BADMISTRAL-1.5B
Base Model(s)	BabyMistral OEvortex/BabyMistral
Model Size	1.5b
Required VRAM	3.1 GB
Updated	2025-09-23
Maintainer	UnfilteredAI
Model Type	mistral
Model Files	3.1 GB
Supported Languages	en
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.45.2
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32002
Torch Data Type	bfloat16

Rank the BADMISTRAL 1.5B 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 BADMISTRAL 1.5B

Best Alternatives	Context / RAM	Downloads	Likes
RakutenAI 2.0 Mini Instruct	128K / 3.1 GB	356	31
RakutenAI 2.0 Mini	128K / 3.1 GB	621	12
... 1.5B Instruct V0.2 Cosmo 100K	32K / 3.1 GB	9	1
RakutenAI 2.0 Mini MLX 4bit	128K / 0.9 GB	24	1
RakutenAI 2.0 Mini MLX 8bit	128K / 1.6 GB	22	1

Note: green Score (e.g. "73.2") means that the model is better than UnfilteredAI/BADMISTRAL-1.5B.