Ctrl K
Back to models

Nex AGI

Nex-N2-Pro

  • Released
  • Open weights
  • Apache 2.0
Compare
Intelligence Index

Reasoning setting

28.2
Estimated · Artificial Analysis v4.3.2
Context window
262K tok

Performance profile

ReasoningRank #25 of 107
89.2%
GPQA Diamond
CodingRank #53 of 94
43.3%
SciCode

Capabilities

Context window

Modalities

Measured setting

Reasoning trade-offs

Source (opens in a new tab)
Intelligence Index v4.3.2
Based on Qwen3.5-397B-A17BEstimated
Intelligence Index
28.2

Pricing & access

No API offering listed in our tracked sources.

Run locally

GGUF
Context
Estimated memory

~248.1 GiB

RAM + VRAM

Estimate assumptions

One text chat at the selected context, with a 16-bit cache and app allowance. Operating system and image processing are extra; optimized caches can use less.

256 GiB RAMwithout GPU offload

Memory budgetOne text chat
Weights
225.2 GiB
Context + state
0.4 GiB16-bit cache
App allowance
22.5 GiB
Download
241.8 GB7 files · keep together+0.9 GB for images (opens in a new tab)
Disk space
~272 GBIncludes image file
Available software
Ollama (opens in a new tab)LM Studio (opens in a new tab)Jan (opens in a new tab)KoboldCpp (opens in a new tab)llama.cpp (opens in a new tab)
Get GGUF (opens in a new tab)
Set up in Ollama · Q4_K_M · 8K context

Save the following as Modelfile. The context matches the estimate above.

FROM hf.co/bartowski/nex-agi_Nex-N2-Pro-GGUF:Q4_K_M
PARAMETER num_ctx 8192

Then run these commands in your terminal:

ollama create llmcurrent-local -f Modelfile
ollama run llmcurrent-local

Ollama import instructions (opens in a new tab) · For LM Studio or Jan, open the app’s model search, enter bartowski/nex-agi_Nex-N2-Pro-GGUF, choose Q4_K_M, and set context to 8,192 tokens in the app’s model settings. Software links above open each app’s setup guide.

Images need extra memoryvLLM setup (opens in a new tab)

Benchmarks

Full leaderboardSource (opens in a new tab)

Humanity’s Last Exam

Frontier reasoning

Nex-N2-Pro · Reasoning#42 of 126

  1. 1Claude Opus 5.5Max61.4%
  2. 2Claude Fable 5.1Max59.1%
  3. 3Gemini 4 ArgonHigh57.1%
  5. 39DeepSeek V4 Flash VisionMax34.5%
  6. 40Apodex 1.1Reasoning34.1%
  7. 41Qwen3.8-27BExtra high33.9%
  8. 42Nex-N2-ProReasoning33.7%
  9. 43LongCat 2.0Reasoning33.7%
  10. 44Agnes 2.5 Pro AlphaReasoning33.6%
  11. 45Hy3Reasoning33.5%

Peers use their best measured result on this benchmark.