What are the hardware requirements for Nex N2.5 Mini?

Nex N2.5 Mini requires approximately 70.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Nex N2.5 Mini and how large is it?

Nex N2.5 Mini is developed by nex-agi, a model with 35.1b 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 Nex N2.5 Mini?

Nex N2.5 Mini is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Nex N2.5 Mini by nex-agi — VRAM 70.4GB

Name: Nex N2.5 Mini
Author: nex-agi

Nex N2.5 Mini is an open-source language model by nex-agi. Features: 35.1b LLM, VRAM: 70.4GB, License: apache-2.0, LLM Explorer Score: 0.43.

Conversational Endpoints compatible Image-text-to-text Qwen3 5 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/nex-agi/Nex-N2.5-mini

Nex N2.5 Mini Parameters and Internals

LLM Name	Nex N2.5 Mini
Repository 🤗	https://huggingface.co/nex-agi/Nex-N2.5-mini
Model Size	35.1b
Required VRAM	70.4 GB
Updated	2026-09-11
Maintainer	nex-agi
Model Type	qwen3_5_moe
Model Files	4.7 GB: 1-of-16 4.0 GB: 2-of-16 5.0 GB: 3-of-16 4.5 GB: 4-of-16 4.0 GB: 5-of-16 5.0 GB: 6-of-16 4.5 GB: 7-of-16 4.0 GB: 8-of-16 5.0 GB: 9-of-16 4.5 GB: 10-of-16 4.0 GB: 11-of-16 5.0 GB: 12-of-16 4.5 GB: 13-of-16 4.0 GB: 14-of-16 5.0 GB: 15-of-16 2.7 GB: 16-of-16
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	5.2.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Nex N2.5 Mini 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

Quantized Models of the Nex N2.5 Mini

Model	Likes	Downloads	VRAM
Nex N2.5 Mini MLX 4bit	6	1077	19 GB
Nex N2.5 Mini OptiQ 4bit	2	282	22 GB
Nex N2.5 Mini MLX 8bit	1	156	37 GB
Nex N2.5 Mini MLX 6bit	1	86	28 GB

Best Alternatives to Nex N2.5 Mini

Best Alternatives	Context / RAM	Downloads	Likes
Agents A1	0K / 70.6 GB	23272	629
Nex N2 Mini	0K / 70.4 GB	2289	294
...l Nova V1.2 Experimental NVFP4	0K / 21.9 GB	161	1
Thomson 1.0 Small	0K / 70.5 GB	214	109
Huihui Agents A1 Abliterated	0K / 70.6 GB	3339	29
Occamy 1.0 FP8	0K / 36.8 GB	445	4
...yJ5ua3Sebfyr8kcVwLAdaiJLUC8pkW	0K / 70.4 GB	1894	0
Nex N2 Mini	0K / 70.4 GB	229	1
Affine 5g4yy75zuz T6	0K / 70.2 GB	756	0
Affine 5ekxlcg3fx Abc	0K / 70.3 GB	863	0