nex-n2.5-max
nex-n2.5-max is We’re on a journey to advance and democratize artificial intelligence through open source and open science.. It is ranked #546 on the Dev Radar, in AI dev tools, first seen 11 days ago and shared in 3 posts (266.4k views).
nex-agi/Nex-N2.5-Max · Hugging Face Hugging Face Log In Sign Up ","eos_token":"<｜end▁of▁sentence｜>","pad_token":"<｜end▁of▁sentence｜>","unk_token":null},"chat_template_jinja":"{% macro render_item_list(item_list, tag_name='required') %}\n {%- if item_list is defined and item_list is iterable and item_list | length > 0 %}\n {%- if tag_name %}{{- '\\n<' ~ tag_name ~ '>' -}}{% endif %}\n {{- '[' }}\n {%- for item in item_list -%}\n {%- if loop.index > 1 %}{{- \", \"}}{% endif -%}\n {%- if item is string -%}\n {{ \"`\" ~ item ~ \"`\" }}\n {%- else -%}\n {{ item }}\n {%- endif -%}\n {%- endfor -%}\n {{- ']' }}\n {%- if tag_name %}{{- '</' ~…
What people said about nex-n2.5-max on X
Meet Nex-N2.5 family, our latest open source agentic models. Mini (35B) and Pro (397B) bring multimodal understanding and computer use. Max (1.6T) is a text-only MoE model built for complex reasoning, coding, and agent workflows. Strong benchmark results in workflow automation and computer use: ⚡ Max scores 50.2 on…
— @NexEcosystem, 11 days ago · 869 likes · see the post
The newly released Nex-N2.5-mini reports 73.4 on Terminal-Bench 2.1 with a 35B / ~3B-active multimodal MoE. ⚡🚀 That puts its published terminal result near Qwen3.8-27B’s 73.0. This looks worth a proper local agent test. I checked the mini model’s config and compared the overlapping public benchmarks, rather than…
— @ViC305, 11 days ago · 52 likes · see the post
Testing Nex-N2.5-Mini (Q4_K_S) on my RTX3080 10GB. This is a 35B A3B MoE, and it barely fits! Only 210 t/s prefill with 50k context. Hmm. I have some tuning to do.
— @PaulGugAI, 10 days ago · 27 likes · see the post
Alternatives to nex-n2.5-max
- muse.ai — New connectors are live today. Come build with us.
- classifier.dev — now outperforms jev and is free
- mimo-v2.6 RL — Streaming the run
- academy.dair.ai — Chat with Paper
- Union Alpha — Union Alpha is a multimodal model built for research, coding, and agentic workflows, while delivering frontier-level…
- cua — Draft #3943
nex-n2.5-max in numbers
- Rank on the Dev Radar: #546 of 1353
- Shared in 3 posts by 3 accounts: @NexEcosystem, @ViC305, @PaulGugAI
- 266.4k views on those posts
- First seen 11 days ago, last shared 10 days ago
- Pricing seen by Jev: open source
- Market: AI dev tools
FAQ
What is nex-n2.5-max?
We’re on a journey to advance and democratize artificial intelligence through open source and open science. It was first shared on X 11 days ago and is ranked #546 on the Dev Radar.
Is nex-n2.5-max free?
It is open source.
Who shared nex-n2.5-max?
3 accounts on X, including @NexEcosystem, @ViC305, @PaulGugAI, in 3 posts totalling 266.4k views.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 12.2k posts from 4.7k X accounts over the last 21 days, 1.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:06 UTC. Full method.