NE

Nex N2.5 Mini

NexGGUF by IsValorumUpdated 2026-10-11
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant14.6 GB
Quick answer

Nex N2.5 Mini needs about 15.7 GB of memory at its main file (a 14.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Nex N2.5 Mini – 34.7B parameter multimodal agentic model

Nex N2.5 Mini is a 34.7B parameter model built on the qwen35moe architecture. It supports vision and long‑horizon agentic tasks with a 262144 token context window. The model is released under the Apache‑2.0 license.

Good at

  • Vision‑based agentic reasoning
  • Long‑horizon task execution
  • Computer and web browsing

Limits

  • Requires ~15.7 GB VRAM at 8k context
  • No explicit GPU requirement beyond VRAM
  • License is Apache‑2.0

Best for

  • Complex productivity workflows
  • Autonomous program execution
  • Multimodal research tasks

Who it’s for. Developers and enterprises looking to integrate a lightweight, vision‑enabled agentic model into applications. The model is open source and can be hosted or run locally with sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—14.6 GB 15.7 GB
Too big Get file →

The only available quant is the unquantized file of 14.56 GB. It requires approximately 15.7 GB of VRAM at 8k context. For 16 GB or larger GPUs, this quant is suitable. No other quants are listed.

What GPU do you need for Nex N2.5 Mini?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is the main file (14.6 GB file, about 15.7 GB in use).

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters34.7B (approximate, mixture of experts)
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized byIsValorum
FamilyNex
Licenseapache-2.0
Downloads (HF)1,768
Last updated2026-10-11

Frequently asked questions about Nex N2.5 Mini

How much VRAM does Nex N2.5 Mini need?

About 15.7 GB at its main file with an 8K context window. That is the 14.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Nex N2.5 Mini on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Nex N2.5 Mini GGUF?

It depends on the quant: file is 14.6 GB.

What context length does Nex N2.5 Mini support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download Nex N2.5 Mini GGUF?

The files are on Hugging Face in the IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Nex N2.5 Mini use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Nex N2.5 Mini on 8 GB VRAM?

The model file is 14.56 GB and requires about 15.7 GB of VRAM at 8k context, so 8 GB VRAM is insufficient.

Does Nex N2.5 Mini support vision?

Yes, the model detects vision abilities and is designed for vision‑based agentic tasks.

Is Nex N2.5 Mini open source?

Yes, the model weights are released under the Apache‑2.0 license and are available on Hugging Face and ModelScope.

Other GGUFs of Nex-N2.5-mini

Similar models

Browse all →

More from IsValorum

All by IsValorum →

More Nex models

All Nex →

Other large models

All large models →