What are the hardware requirements for Poulpe Gen1 14B MLX 4bit?

Poulpe Gen1 14B MLX 4bit requires approximately 7.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Poulpe Gen1 14B MLX 4bit and how large is it?

Poulpe Gen1 14B MLX 4bit is developed by intuitem, a model with 14b 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 Poulpe Gen1 14B MLX 4bit?

Poulpe Gen1 14B MLX 4bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Poulpe Gen1 14B MLX 4bit by intuitem — VRAM 7.6GB

Name: Poulpe Gen1 14B MLX 4bit
Author: intuitem

Poulpe Gen1 14B MLX 4bit is an open-source language model by intuitem. Features: 14b LLM, VRAM: 7.6GB, License: apache-2.0, Quantized.

4-bit 4bit Anssi Base model:intuitem/poulpe-gen... Base model:quantized:intuitem/... Conversational Cybersecurity Ebios-rm En Fr Grc Iso-27005 Mistral3 Mlx Quantized Region:us Risk-management Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/intuitem/Poulpe-Gen1-14B-MLX-4bit

Poulpe Gen1 14B MLX 4bit Parameters and Internals

LLM Name	Poulpe Gen1 14B MLX 4bit
Repository 🤗	https://huggingface.co/intuitem/Poulpe-Gen1-14B-MLX-4bit
Base Model(s)	Poulpe Gen1 14B intuitem/Poulpe-Gen1-14B
Model Size	14b
Required VRAM	7.6 GB
Updated	2026-10-27
Maintainer	intuitem
Model Type	mistral3
Model Files	5.4 GB: 1-of-2 2.2 GB: 2-of-2
Supported Languages	fr en
Quantization Type	4bit
Model Architecture	Mistral3ForConditionalGeneration
License	apache-2.0
Transformers Version	5.0.0
Tokenizer Class	TokenizersBackend
Padding Token	<pad>

Rank the Poulpe Gen1 14B MLX 4bit 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 Poulpe Gen1 14B MLX 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Ministral 3 14B Abliterated	0K / 28 GB	347	1
...s Abliterated V2 Base And GGUF	0K / 28 GB	289	2
Amaretto 14B	0K / 28 GB	691	3
... 14B Reasoning 2512 Uncensored	0K / 28 GB	19	0
... 3 14B Instruct 2512 MLX MXFP4	0K / 7.2 GB	526	2
Ministral 3 14B Base 2512	0K / 28 GB	132	0
Ministral 3 14B Abliterated	0K / 28 GB	46	5
Ministral 3 14B Instruct 2512	0K / 27 GB	60	1

Note: green Score (e.g. "73.2") means that the model is better than intuitem/Poulpe-Gen1-14B-MLX-4bit.