{"id":5080,"date":"2026-09-27T06:52:34","date_gmt":"2026-09-26T21:52:34","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/publisher-nous-en\/"},"modified":"2026-09-27T07:21:11","modified_gmt":"2026-09-26T22:21:11","slug":"publisher-nous-en","status":"publish","type":"page","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/publisher-nous-en\/","title":{"rendered":"Nous Research Open Models: Model List and Licenses"},"content":{"rendered":"<h2>About Nous Research<\/h2>\n<p><strong>Nous Research<\/strong> is a research organization that releases <strong>conversational and reasoning models built by further training base models released by others<\/strong>, through its <a href=\"https:\/\/huggingface.co\/NousResearch\">NousResearch organization on Hugging Face<\/a>. Its flagship <strong>Hermes<\/strong> series has long been popular among local LLM users.<\/p>\n<h2>What It Releases<\/h2>\n<ul>\n<li><strong>Hermes 4<\/strong> (August 2025): 70B and 405B based on Llama 3.1, plus a 14B.<\/li>\n<li><strong>Hermes 4.3 36B<\/strong> (November 2025): according to its model card, a hybrid-mode reasoning model based on ByteDance&#8217;s Seed-OSS-36B, and <strong>the first Hermes model trained in a decentralized manner over the internet using Psyche<\/strong>.<\/li>\n<li><strong>NousCoder-14B<\/strong> (December 2025): a model for coding.<\/li>\n<li>Earlier lines include Hermes 3 (based on Llama 3.1 and 3.2) and DeepHermes 3 (based on Llama 3 and Mistral).<\/li>\n<\/ul>\n<h2>Licenses<\/h2>\n<p><strong>Models inherit the license of their base model.<\/strong> Llama-based models use the Llama 3 license, and those based on Seed-OSS and Mistral are Apache-2.0. Models based on Kimi K2 keep its Modified MIT license. Read each model&#8217;s license text before use. This summary is not legal advice.<\/p>\n<h2>Running Them Locally<\/h2>\n<ul>\n<li><strong>Official GGUF builds are plentiful.<\/strong> Nous Research itself publishes GGUF files for Hermes 4.3 36B, DeepHermes 3, Hermes 3 and more, and official FP8 builds for the large models.<\/li>\n<li><strong>On a consumer GPU, quantized Hermes 4.3 36B or the 3B and 8B DeepHermes are the candidates.<\/strong> The 70B and 405B are data-center sizes.<\/li>\n<\/ul>\n<p><em>Sources: the model card of <a href=\"https:\/\/huggingface.co\/NousResearch\/Hermes-4.3-36B\">NousResearch\/Hermes-4.3-36B<\/a>; the model list of the NousResearch organization on Hugging Face (all as of 2026-09-26).<\/em><\/p>\n<h2>Our Coverage and Data<\/h2>\n<p>Local Model Watch has not published an article on Nous Research&#8217;s models yet. The model list below is collected by code from Hugging Face every day. Part of our <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/publishers-en\/\">publisher index<\/a>; model families link to their <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/models-en\/\">family pages<\/a>.<\/p>\n<h2>At a Glance<\/h2>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Item<\/th>\n<th>Value<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Hugging Face organization<\/td>\n<td><a href=\"https:\/\/huggingface.co\/NousResearch\">NousResearch<\/a><\/td>\n<\/tr>\n<tr>\n<td>Models on Hugging Face<\/td>\n<td>126<\/td>\n<\/tr>\n<tr>\n<td>Articles on its own models<\/td>\n<td>0<\/td>\n<\/tr>\n<tr>\n<td>Articles on derived models<\/td>\n<td>0<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<h2>Recent Models on Hugging Face<\/h2>\n<p>The publisher lists <strong>126 models<\/strong> in total on Hugging Face. Below are up to 15 of the most recent generative models (text, image, video, audio and so on), the scope of this site, per organization. Classifiers, feature extractors, research components and repositories without a model card are omitted, and the publisher&#8217;s own quantized builds and helper variants are folded into the row of the original model. Parameter counts are left blank for repositories that pack weights into integer types, where Hugging Face&#8217;s count is not the real parameter count.<\/p>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<p class=\"lmw-table-hint\" style=\"margin:0 0 4px;font-size:0.85em;opacity:0.7;\">\u2192 Scroll horizontally to see all columns<\/p>\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Released<\/th>\n<th>Model<\/th>\n<th>Task<\/th>\n<th>Parameters<\/th>\n<th>License<\/th>\n<th>Official variants<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>2025-12-23<\/td>\n<td><a href=\"https:\/\/huggingface.co\/NousResearch\/NousCoder-14B\">NousResearch\/NousCoder-14B<\/a><\/td>\n<td>text generation<\/td>\n<td>14.8B<\/td>\n<td><code>apache-2.0<\/code><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>2025-12-07<\/td>\n<td><a href=\"https:\/\/huggingface.co\/NousResearch\/nomos-1\">NousResearch\/nomos-1<\/a><\/td>\n<td>text generation<\/td>\n<td>30.5B<\/td>\n<td><code>apache-2.0<\/code><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>2025-11-18<\/td>\n<td><a href=\"https:\/\/huggingface.co\/NousResearch\/Hermes-4.3-36B\">NousResearch\/Hermes-4.3-36B<\/a><\/td>\n<td>text generation<\/td>\n<td>36.2B<\/td>\n<td><code>apache-2.0<\/code><\/td>\n<td>GGUF<\/td>\n<\/tr>\n<tr>\n<td>2025-11-08<\/td>\n<td><a href=\"https:\/\/huggingface.co\/NousResearch\/k2-merged-3.5T-fp8\">NousResearch\/k2-merged-3.5T-fp8<\/a><\/td>\n<td>text generation<\/td>\n<td>\u2014<\/td>\n<td><code>modified-mit<\/code><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>2025-09-12<\/td>\n<td><a href=\"https:\/\/huggingface.co\/NousResearch\/k2-merged-3.5T-bf16\">NousResearch\/k2-merged-3.5T-bf16<\/a><\/td>\n<td>text generation<\/td>\n<td>3468.1B<\/td>\n<td><code>modified-mit<\/code><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>2025-08-31<\/td>\n<td><a href=\"https:\/\/huggingface.co\/NousResearch\/Hermes-4-14B\">NousResearch\/Hermes-4-14B<\/a><\/td>\n<td>text generation<\/td>\n<td>\u2014<\/td>\n<td><code>apache-2.0<\/code><\/td>\n<td>FP8<\/td>\n<\/tr>\n<tr>\n<td>2025-08-19<\/td>\n<td><a href=\"https:\/\/huggingface.co\/NousResearch\/Hermes-4-70B\">NousResearch\/Hermes-4-70B<\/a><\/td>\n<td>text generation<\/td>\n<td>70.6B<\/td>\n<td><code>llama3<\/code><\/td>\n<td>FP8<\/td>\n<\/tr>\n<tr>\n<td>2025-08-06<\/td>\n<td><a href=\"https:\/\/huggingface.co\/NousResearch\/Hermes-4-405B\">NousResearch\/Hermes-4-405B<\/a><\/td>\n<td>text generation<\/td>\n<td>405.9B<\/td>\n<td><code>llama3<\/code><\/td>\n<td>FP8<\/td>\n<\/tr>\n<tr>\n<td>2025-04-28<\/td>\n<td><a href=\"https:\/\/huggingface.co\/NousResearch\/DeepHermes-Financial-Fundamentals-Prediction-Specialist-Atropos\">NousResearch\/DeepHermes-Financial-Fundamentals-Prediction-Specialist-Atropos<\/a><\/td>\n<td>text generation<\/td>\n<td>8.0B<\/td>\n<td><code>llama3<\/code><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>2025-03-02<\/td>\n<td><a href=\"https:\/\/huggingface.co\/NousResearch\/DeepHermes-3-Mistral-24B-Preview\">NousResearch\/DeepHermes-3-Mistral-24B-Preview<\/a><\/td>\n<td>text generation<\/td>\n<td>23.6B<\/td>\n<td><code>apache-2.0<\/code><\/td>\n<td>GGUF<\/td>\n<\/tr>\n<tr>\n<td>2025-02-17<\/td>\n<td><a href=\"https:\/\/huggingface.co\/NousResearch\/DeepHermes-3-Llama-3-3B-Preview\">NousResearch\/DeepHermes-3-Llama-3-3B-Preview<\/a><\/td>\n<td>text generation<\/td>\n<td>3.2B<\/td>\n<td><code>llama3<\/code><\/td>\n<td>GGUF<\/td>\n<\/tr>\n<tr>\n<td>2025-02-12<\/td>\n<td><a href=\"https:\/\/huggingface.co\/NousResearch\/DeepHermes-3-Llama-3-8B-Preview\">NousResearch\/DeepHermes-3-Llama-3-8B-Preview<\/a><\/td>\n<td>text generation<\/td>\n<td>8.0B<\/td>\n<td><code>llama3<\/code><\/td>\n<td>GGUF<\/td>\n<\/tr>\n<tr>\n<td>2024-12-04<\/td>\n<td><a href=\"https:\/\/huggingface.co\/NousResearch\/Hermes-3-Llama-3.2-3B\">NousResearch\/Hermes-3-Llama-3.2-3B<\/a><\/td>\n<td>text generation<\/td>\n<td>3.2B<\/td>\n<td><code>llama3<\/code><\/td>\n<td>GGUF<\/td>\n<\/tr>\n<tr>\n<td>2024-09-27<\/td>\n<td><a href=\"https:\/\/huggingface.co\/NousResearch\/Llama-3.2-1B\">NousResearch\/Llama-3.2-1B<\/a><\/td>\n<td>text generation<\/td>\n<td>1.2B<\/td>\n<td><code>llama3.2<\/code><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>2024-08-13<\/td>\n<td><a href=\"https:\/\/huggingface.co\/NousResearch\/Hermes-3-Llama-3.1-405B\">NousResearch\/Hermes-3-Llama-3.1-405B<\/a><\/td>\n<td>text generation<\/td>\n<td>405.9B<\/td>\n<td><code>llama3<\/code><\/td>\n<td>FP8<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><em>From the Hugging Face API. Last changed 2026-09-27 (JST). Collected by code.<\/em><\/p>\n<p><em>Last updated 2026-09-27 (JST). The explanation at the top of this page was written with the help of AI from the primary sources it cites. The tables and lists under &#8220;Our Coverage and Data&#8221; are assembled by code from our article log and the Hugging Face API.<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"<p>About Nous Research Nous Research is a research organization that releases conversational and reasoning models built by further training base models released by others, through its NousResearch organization on Hugging Face. Its flagship Hermes series has long been popular among local LLM users. What It Releases Hermes 4 (August 2025): 70B and 405B based on [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-5080","page","type-page","status-publish","hentry"],"lang":"en","translations":{"en":5080,"ja":5079},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/pages\/5080","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/comments?post=5080"}],"version-history":[{"count":1,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/pages\/5080\/revisions"}],"predecessor-version":[{"id":5164,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/pages\/5080\/revisions\/5164"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=5080"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}