LocalClaw/LLM/Nex-N2.5-mini
Open-weight MoE

Nex-N2.5-mini

Catalogue summary: Official Nex-AGI Apache 2.0 multimodal agent model for computer use, web browsing, coding and tool calling. Community Q4_K_M GGUF is about 21.3GB with documented llama.cpp text and vision smoke tests.

Repository editorial metadata; verify comparative claims in the linked upstream material.

32 GB catalogue minimum32 GB RAMQ4_K_MCoding assistant
Choose an app

Pick the app you already use. No terminal and no command to copy.

Compare models
Open in LM StudioOpens the app on this model's download screenOpen in UnslothLaunches Unsloth Desktop on this model's download page
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloadsOpen llama.cpp setupAdvanced option: opens the model filesUse with LocalClawOptional workspace after the model is installed

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Parameters
35B MoE
Minimum RAM
32 GB
Model size
21.3 GB
Quantization
Q4_K_M

Can Nex-N2.5-mini run locally?

Nex-N2.5-mini has a catalogue minimum of 32 GB RAM with Q4_K_M. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Use nex-n2.5-mini as the catalogue search term in a compatible runtime, and confirm the available format on the upstream repository before download.

Model sourcePublic GGUF repository (verified 2026-09-23): mradermacher/Nex-N2.5-mini-i1-GGUFUpstream releasePaper or model cardLicence text
chatcodereasoningvisionagenticpowerlong-contexttool-calling

Install path

01
Check RAM fitMinimum 32 GB RAM. Start with the Q4_K_M quant.
02
Load the modelSearch nex-n2.5-mini in LM Studio.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Catalogue record

  • Family: nex
  • Parameters: 35B MoE
  • Recommended quantization: Q4_K_M
  • Catalogue minimum RAM: 32 GB
  • Catalogue model size: 21.3 GB
  • Tags: chat, code, reasoning, vision, agentic, power, long-context, tool-calling

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Catalogue tags

  • chat
  • code
  • reasoning
  • vision
  • agentic
  • power

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
6
quality
9
coding
9
reasoning
9

Technical notes

Developer
Nex-AGI
License
Apache 2.0
Context window
262,144 tokens
Architecture
Multimodal Qwen3.5-style Mixture-of-Experts model. Community GGUF notes identify 256 experts, 8 active experts per token, 40 text layers and a 262,144-token text context configuration.

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Comfortable headroomMac mini M4 Pro 48GBMobile workstationMacBook Pro M4 Max 36GBPower-user picks32GB RAM guide

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

Occamy-1.0 35B (3B active, MoE)Qwen 3.6 35B-A3B 35B (3B active, MoE)Qwen3.8-27B 27BXing4.0-29B-A4B 29B (4B active, MoE)Muse Glimmer 30B 29.8B multimodalNemotron 3.5 Lightning 30B-A3B 30B (3B active, MoE)Agents-A1 4B 4BAgents-A1 35B (3B active, MoE)

Where to go next