NE

Source Hf Nex N2.5 Mini

NexGGUF by ngquocvinhUpdated 2026-09-13
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant5.3 GB
Quick answer

Source Hf Nex N2.5 Mini needs about 22.3 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 15 quants, from 5.3 GB (Q1_0) to 36.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Source Hf Nex N2.5 Mini – a 34.7B‑parameter multimodal, agent‑oriented model

Source Hf Nex N2.5 Mini is a 34.7‑billion‑parameter Qwen3.5 Mixture‑of‑Experts model. It supports vision, tools, and long‑horizon tasks with a 262,144‑token context. The model is released under the Apache‑2.0 license.

Good at

  • Vision‑guided agentic tasks
  • Tool calling and web browsing
  • Long‑horizon reasoning

Limits

  • No text‑only inference without vision projector
  • Requires 8,096‑token context for full validation
  • Large VRAM needed for higher quants

Best for

  • Autonomous computer use
  • Multimodal research prototypes
  • Complex productivity workflows

Who it’s for. Developers building agentic applications that need vision and tool use. Researchers exploring multimodal long‑horizon reasoning. Enterprises seeking open‑source, agent‑oriented models.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q1_05.3 GB 6.5 GB
Fits Get file →
IQ1_M8.2 GB 9.4 GB
Too big Get file →
IQ2_XS10.5 GB 11.7 GB
Too big Get file →
Q2_K_S12.2 GB 13.3 GB
Too big Get file →
Q2_K12.9 GB 14.1 GB
Too big Get file →
IQ3_S15.3 GB 16.4 GB
Too big Get file →
IQ3_M15.4 GB 16.6 GB
Too big Get file →
Q3_K_M16.8 GB 17.9 GB
Too big Get file →
Q3_K_L18.1 GB 19.3 GB
Too big Get file →
IQ4_XS18.7 GB 19.9 GB
Too big Get file →
IQ4_NL19.8 GB 21.0 GB
Too big Get file →
Q4_K_M21.2 GB 22.3 GB
Too big Get file →
Q5_K_M24.7 GB 25.9 GB
Too big Get file →
Q6_K28.5 GB 29.7 GB
Too big Get file →
Q8_036.9 GB 38.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 21.17 GB, memory 22.3 GB at 8k context). For 12 GB VRAM, use Q5_K_M (24.73 GB, 25.9 GB). For 16 GB VRAM, use Q6_K (28.51 GB, 29.7 GB). Estimates are approximate.

What GPU do you need for Source Hf 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: the best quant that fits is Q1_0 (5.3 GB file, about 6.5 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_XS (10.5 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q2_K (12.9 GB file, about 14.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (21.2 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.5 GB file, about 29.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (36.9 GB file, about 38.1 GB in use).

Which Source Hf Nex N2.5 Mini quant should you choose?

Q4_K_M is the usual starting point for Source Hf Nex N2.5 Mini: it balances file size and quality well. Here it is a 21.2 GB file.

The Q8_0 file is 36.9 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q1_0 at 5.3 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

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 byngquocvinh
FamilyNex
Licenseapache-2.0
Downloads (HF)2,016
Last updated2026-09-13

Frequently asked questions about Source Hf Nex N2.5 Mini

How much VRAM does Source Hf Nex N2.5 Mini need?

About 22.3 GB at Q4_K_M with an 8K context window. That is the 21.2 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 Source Hf Nex N2.5 Mini on an 8 GB GPU?

Yes, with Q1_0: the 5.3 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: Q1_0 is 5.3 GB, IQ1_M is 8.2 GB, IQ2_XS is 10.5 GB, Q2_K_S is 12.2 GB, Q2_K is 12.9 GB, IQ3_S is 15.3 GB and 9 more.

What context length does Source Hf 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 Source Hf Nex N2.5 Mini GGUF?

The files are on Hugging Face in the ngquocvinh/Nex-N2.5-mini-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 Source Hf 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 Source Hf Nex N2.5 Mini on 8 GB VRAM?

Use the Q4_K_M quant, which requires about 22.3 GB of VRAM at 8k context. It is the smallest quant that supports the full model.

Does this model support vision?

Yes, it supports vision and requires the separate mmproj-Nex-N2.5-mini-F16.gguf projector.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Nex-N2.5-mini

Similar models

Browse all →

More from ngquocvinh

All by ngquocvinh →

More Nex models

All Nex →

Other large models

All large models →