{"id":15137,"date":"2026-11-17T11:03:26","date_gmt":"2026-11-17T02:03:26","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/?p=15137"},"modified":"2026-11-17T11:13:01","modified_gmt":"2026-11-17T02:13:01","slug":"ripple-65b-preview-released","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/ripple-65b-preview-released\/","title":{"rendered":"Ripple-65B-Preview Agentic Coding-Focused Dense Model: 32GB+ VRAM"},"content":{"rendered":"<p><!-- lmw:facts --><\/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>Repository<\/td>\n<td><a href=\"https:\/\/huggingface.co\/ricursiveAI\/Ripple-65B-Preview\">ricursiveAI\/Ripple-65B-Preview<\/a><\/td>\n<\/tr>\n<tr>\n<td>Family guide<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/model-ricursiveai-ripple-en\/\">Ripple guide (1 articles)<\/a><\/td>\n<\/tr>\n<tr>\n<td>Published<\/td>\n<td>2026-11-04<\/td>\n<\/tr>\n<tr>\n<td>License<\/td>\n<td>apache-2.0<\/td>\n<\/tr>\n<tr>\n<td>Formats<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/format-safetensors-en\/\">safetensors<\/a><\/td>\n<\/tr>\n<tr>\n<td>Source type<\/td>\n<td>Primary source (the publisher itself)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><em>Values determined by this site&#8217;s code when the information was collected. Dates are JST.<\/em><\/p>\n<p><!-- \/lmw:facts --><\/p>\n<h2>Overview<\/h2>\n<p>Ricursive Intelligence has released &#8220;Ripple-65B Preview&#8221;, a 65B parameter dense model pre-trained on 12 trillion tokens that supports a context length of up to 1M. It is designed to deliver strong results in agentic coding tasks. According to the model card, it scores 80.52 on Terminal-Bench 2.1, an indicator for agent terminal operation, reportedly outperforming larger U.S. open-weight models.<\/p>\n<h2>Specifications<\/h2>\n<ul>\n<li>Architecture: Dense Transformer<\/li>\n<li>Number of Parameters: 65B<\/li>\n<li>Number of Active Parameters: 65B<\/li>\n<li>Context Length: Up to 1M<\/li>\n<li>Pre-training Tokens: 12 trillion tokens<\/li>\n<li>Features: Adopts a &#8220;thin-and-deep&#8221; aspect ratio with a hidden layer dimension (d_model) of 5120 and a total of 80 layers. It also incorporates features from the Gemma 3N family architecture, over-allocated attention heads, FFN activation clipping, gated attention, global NoPE, and value residuals.<\/li>\n<\/ul>\n<h2>Performance<\/h2>\n<p>Below is the comparison table of instruct model benchmarks with U.S. open-weight frontier models as stated in the model card. The comparison targets are Nemotron 3 Ultra 550B, Inkling 975B, Muse Spark Open 816B, and Reflection Beam 501B.<\/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>Benchmark<\/th>\n<th>Ripple-65B Preview<\/th>\n<th>Nemotron 3 Ultra 550B<\/th>\n<th>Inkling 975B<\/th>\n<th>Muse Spark Open 816B<\/th>\n<th>Reflection Beam 501B<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td><strong>Model<\/strong><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>Architecture<\/td>\n<td>Dense<\/td>\n<td>MoE<\/td>\n<td>MoE<\/td>\n<td>MoE<\/td>\n<td>MoE<\/td>\n<\/tr>\n<tr>\n<td>Total params<\/td>\n<td>65B<\/td>\n<td>550B<\/td>\n<td><strong>975B<\/strong><\/td>\n<td>816B<\/td>\n<td>501B<\/td>\n<\/tr>\n<tr>\n<td>Active params<\/td>\n<td><strong>65B<\/strong><\/td>\n<td>55B<\/td>\n<td>41B<\/td>\n<td>42B<\/td>\n<td>23B<\/td>\n<\/tr>\n<tr>\n<td>Pre-training tokens<\/td>\n<td>12T<\/td>\n<td>20T<\/td>\n<td><strong>45T<\/strong><\/td>\n<td>N\/A<\/td>\n<td>23.8T<\/td>\n<\/tr>\n<tr>\n<td><strong>Knowledge<\/strong><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>MMLU<\/td>\n<td>89.6<\/td>\n<td><em>92.0<\/em><\/td>\n<td><em>91.3<\/em><\/td>\n<td><strong><em>92.6<\/em><\/strong><\/td>\n<td><em>92.4<\/em><\/td>\n<\/tr>\n<tr>\n<td>MMLU-Pro<\/td>\n<td>84.2<\/td>\n<td>86.8<\/td>\n<td><em>87.3<\/em><\/td>\n<td><strong><em>87.9<\/em><\/strong><\/td>\n<td><em>76.5<\/em><\/td>\n<\/tr>\n<tr>\n<td>GPQA Diamond<\/td>\n<td>85.2<\/td>\n<td>87.0<\/td>\n<td>87.2<\/td>\n<td>89.0<\/td>\n<td><strong>90.6<\/strong><\/td>\n<\/tr>\n<tr>\n<td><strong>Math<\/strong><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>AIME 2024<\/td>\n<td>97.1<\/td>\n<td><em>94.2<\/em><\/td>\n<td><em>97.5<\/em><\/td>\n<td><strong><em>97.9<\/em><\/strong><\/td>\n<td><em>96.7<\/em><\/td>\n<\/tr>\n<tr>\n<td>AIME 2025<\/td>\n<td>98.3<\/td>\n<td><em>94.2<\/em><\/td>\n<td><em>91.7<\/em><\/td>\n<td><strong><em>100.0<\/em><\/strong><\/td>\n<td><em>99.6<\/em><\/td>\n<\/tr>\n<tr>\n<td>AIME 2026<\/td>\n<td>95.0<\/td>\n<td><em>95.4<\/em><\/td>\n<td>97.1<\/td>\n<td><strong><em>98.3<\/em><\/strong><\/td>\n<td>97.7<\/td>\n<\/tr>\n<tr>\n<td>HMMT Feb 2026<\/td>\n<td>90.5<\/td>\n<td><em>80.3<\/em><\/td>\n<td>86.3<\/td>\n<td><strong><em>93.9<\/em><\/strong><\/td>\n<td><strong><em>93.9<\/em><\/strong><\/td>\n<\/tr>\n<tr>\n<td><strong>Coding &amp; Agentic<\/strong><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>Terminal-Bench 2.1 (self-reported)<\/td>\n<td><strong>80.5<\/strong><\/td>\n<td>56.4<\/td>\n<td>63.8<\/td>\n<td>76.4<\/td>\n<td>80.1<\/td>\n<\/tr>\n<tr>\n<td>Terminal-Bench 2.1 (Terminus 2)<\/td>\n<td><strong>80.5<\/strong><\/td>\n<td><em>55.1<\/em><\/td>\n<td><em>56.2<\/em><\/td>\n<td><em>78.7<\/em><\/td>\n<td><em>70.8<\/em><\/td>\n<\/tr>\n<tr>\n<td>SWE-bench Verified<\/td>\n<td>76.5<\/td>\n<td>71.9<\/td>\n<td>77.6<\/td>\n<td><em>78.7<\/em><\/td>\n<td><strong>81.6<\/strong><\/td>\n<\/tr>\n<tr>\n<td>SWE-bench Pro v1.0<\/td>\n<td>61.42<\/td>\n<td><em>46.9<\/em><\/td>\n<td>54.3<\/td>\n<td><em>58.2<\/em><\/td>\n<td><strong>66.1<\/strong><\/td>\n<\/tr>\n<tr>\n<td>SWE-bench Pro v2.0 Hard<\/td>\n<td><strong>79.1<\/strong><\/td>\n<td><em>30.7<\/em><\/td>\n<td><em>2.0<\/em><\/td>\n<td><em>52.3<\/em><\/td>\n<td>76.5<\/td>\n<\/tr>\n<tr>\n<td>DeepSWE 1.1<\/td>\n<td>44.3<\/td>\n<td><em>0.2<\/em><\/td>\n<td><em>1.8<\/em><\/td>\n<td><strong>60.0<\/strong><\/td>\n<td>43.3<\/td>\n<\/tr>\n<tr>\n<td>SciCode (Inspect AI)<\/td>\n<td>39.4<\/td>\n<td>44.6<\/td>\n<td>46.1<\/td>\n<td><strong>58.5<\/strong><\/td>\n<td>49.2<\/td>\n<\/tr>\n<tr>\n<td>\u03c4\u00b3-bench banking<\/td>\n<td>31.27<\/td>\n<td>22.6<\/td>\n<td>23.7<\/td>\n<td><em>14.4<\/em><\/td>\n<td><strong>36.1<\/strong><\/td>\n<\/tr>\n<tr>\n<td>AutomationBench (Public)<\/td>\n<td>36.4<\/td>\n<td><em>8.4<\/em><\/td>\n<td><em>14.6<\/em><\/td>\n<td><em>42.4<\/em><\/td>\n<td>39.3<\/td>\n<\/tr>\n<tr>\n<td>MCP Atlas<\/td>\n<td>71.67<\/td>\n<td><em>62.2<\/em><\/td>\n<td>76.0<\/td>\n<td><strong>89.2<\/strong><\/td>\n<td>80.8<\/td>\n<\/tr>\n<tr>\n<td><strong>Safety<\/strong><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>FORTRESS Adversarial<\/td>\n<td>83.8<\/td>\n<td><em>79.3<\/em><\/td>\n<td>78.0<\/td>\n<td>*<em>94.2<\/em><\/td>\n<td><em>92.1<\/em><\/td>\n<\/tr>\n<tr>\n<td>FORTRESS Benign<\/td>\n<td>95.5<\/td>\n<td><em>89.1<\/em><\/td>\n<td><strong>95.9<\/strong><\/td>\n<td><em>82.6<\/em><\/td>\n<td><em>86.4<\/em><\/td>\n<\/tr>\n<tr>\n<td>StrongREJECT<\/td>\n<td>97.5<\/td>\n<td><em>98.2<\/em><\/td>\n<td><strong>98.6<\/strong><\/td>\n<td><em>94.7<\/em><\/td>\n<td><em>95.8<\/em><\/td>\n<\/tr>\n<tr>\n<td><strong>Instruction Following<\/strong><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>IFBench<\/td>\n<td>79.2<\/td>\n<td>*<em>81.7<\/em><\/td>\n<td>79.8<\/td>\n<td><em>78.6<\/em><\/td>\n<td>79.6<\/td>\n<\/tr>\n<tr>\n<td><strong>Long Context<\/strong><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>AA-LCR<\/td>\n<td>75.0<\/td>\n<td>65.4<\/td>\n<td><em>78.3<\/em><\/td>\n<td><strong><em>80.7<\/em><\/strong><\/td>\n<td>78.2<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>According to measurements published by the model creator, Ripple-65B Preview achieves high scores in coding and agent-related tasks (such as Terminal-Bench 2.1 and SWE-bench Pro v2.0 Hard) that rival or exceed models much larger than itself. On the other hand, in some categories such as MMLU measuring general knowledge, GPQA Diamond which consists of difficult scientific questions, and safety indicators like FORTRESS Adversarial and StrongREJECT, it shows lower results compared to comparison models such as Muse Spark Open and Reflection Beam. It is not an all-purpose model, but rather configured to have strengths in specific coding and reasoning tasks.<\/p>\n<h2>Strengths and Use Cases<\/h2>\n<p>Ripple-65B Preview is a model designed specifically for agentic coding and advanced reasoning tasks. It supports a context length of up to 1M, making it suitable for long-document reading and tasks involving massive codebases. According to the model card and blog, it adopts a dense Transformer architecture for efficient training and serving, and is built aiming for development by small teams and efficient operation on hardware. Note that this pre-release version places a particular emphasis on agentic coding.<\/p>\n<p><!-- lmw:hardware --><\/p>\n<h2>Hardware Requirements<\/h2>\n<p><strong>Estimated requirements (calculated by Local Model Watch)<\/strong> \u2014 64.8B parameters<\/p>\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>Your VRAM<\/th>\n<th>Quantization<\/th>\n<th>File size<\/th>\n<th>Est. memory needed<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>32GB (RTX 5090, etc.)<\/td>\n<td>Q2_K<\/td>\n<td>22.1GB<\/td>\n<td>26.5GB<\/td>\n<\/tr>\n<tr>\n<td>48GB (RTX 6000 Ada \/ A6000, etc.)<\/td>\n<td>Q4_K_M<\/td>\n<td>36.1GB<\/td>\n<td>43.4GB<\/td>\n<\/tr>\n<tr>\n<td>80GB class (A100 \/ H100)<\/td>\n<td>Q8_0<\/td>\n<td>64.1GB<\/td>\n<td>76.9GB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><strong>Inference engine support<\/strong> (architecture name matched against each project&#8217;s own model registry in its source code, checked 2026-11-17): llama.cpp: registered, vLLM: registered, MLX (mlx-lm): not registered. &#8220;Not registered&#8221; means the name is absent from that registry today, not that the model cannot run.<\/p>\n<p><em>Memory estimates add a 20% runtime overhead (KV cache, etc.) to the actual size of the distributed files. Actual usage varies with context length, batch size and inference engine. These figures are computed by this site from file sizes, not published by the model&#8217;s authors. File sizes are measured from the converted build <a href=\"https:\/\/huggingface.co\/DevQuasar\/ricursiveAI.Ripple-65B-Preview-GGUF\">DevQuasar\/ricursiveAI.Ripple-65B-Preview-GGUF<\/a>. Compare with other models in our <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/vram-guide-en\/\">VRAM quick reference<\/a>. What the quantization names mean: <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/glossary-quantization-en\/\">glossary<\/a>.<\/em><\/p>\n<p><!-- \/lmw:hardware --><\/p>\n<p><!-- lmw:runnability --><\/p>\n<h2>Can You Run It Locally?<\/h2>\n<p>The publisher distributes this model as safetensors.<\/p>\n<p><strong>License \u2014 <code>apache-2.0<\/code> (Commercial use allowed):<\/strong> Permits commercial use, modification and redistribution. Redistribution requires including the license and stating changes; includes a patent grant.<\/p>\n<p><strong>Compression:<\/strong> the Q2_K build measures 2.93 bits per weight \u2014 about 18% the size of the original 16-bit weights, calculated by this site from the actual file sizes.<\/p>\n<p><em>Compiled by this site&#8217;s code from the published formats and the license field. License summaries are not legal advice \u2014 check the publisher&#8217;s original terms before relying on them.<\/em><\/p>\n<p><!-- \/lmw:runnability --><\/p>\n<h2>How to Get It<\/h2>\n<p>It is available from the official Hugging Face repository. The Apache 2.0 license is applied, allowing use under specified conditions including commercial use. The repository provides a BF16 instruct model, along with NVFP4 checkpoints and Google Colab. It is also available from external platforms such as Together AI, GMI Cloud, and OpenRouter.<\/p>\n<p><!-- lmw:variants --><\/p>\n<h2>Quantized and Converted Variants<\/h2>\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>Added<\/th>\n<th>Publisher<\/th>\n<th>Format<\/th>\n<th>Repository<\/th>\n<th>Smallest VRAM tier (build, est. memory)<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>2026-11-17<\/td>\n<td>ricursiveAI<\/td>\n<td>NVFP4<\/td>\n<td><a href=\"https:\/\/huggingface.co\/ricursiveAI\/Ripple-65B-Preview-NVFP4\">ricursiveAI\/Ripple-65B-Preview-NVFP4<\/a><\/td>\n<td>NVFP4 63.9GB (fits in 80GB VRAM)<\/td>\n<\/tr>\n<tr>\n<td>2026-11-17<\/td>\n<td>DevQuasar<\/td>\n<td>GGUF<\/td>\n<td><a href=\"https:\/\/huggingface.co\/DevQuasar\/ricursiveAI.Ripple-65B-Preview-GGUF\">DevQuasar\/ricursiveAI.Ripple-65B-Preview-GGUF<\/a><\/td>\n<td>Q2_K 26.5GB (fits in 32GB VRAM)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>File sizes of each build:<\/p>\n<ul>\n<li>Available builds in ricursiveAI\/Ripple-65B-Preview-NVFP4: NVFP4 53.3GB<\/li>\n<li>Available builds in DevQuasar\/ricursiveAI.Ripple-65B-Preview-GGUF: Q2_K 22.1GB \/ Q3_K_M 28.9GB \/ Q4_K_M 36.1GB \/ Q5_K_M 42.6GB \/ Q6_K 49.5GB \/ Q8_0 64.1GB<\/li>\n<\/ul>\n<p>In addition, 43 converted build(s) from other uploaders exist on Hugging Face; this site lists only builds from the model&#8217;s publisher or established quantization maintainers.<\/p>\n<p><em>This section is appended automatically by Local Model Watch when a converted build of this model appears after publication. Memory figures are estimated from the size of the distributed files. What the quantization names mean: <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/glossary-quantization-en\/\">glossary<\/a>.<\/em><\/p>\n<p><!-- \/lmw:variants --><\/p>\n<p><!-- lmw:next-steps --><\/p>\n<h2>What to Read Next<\/h2>\n<ul>\n<li><strong>Find models by VRAM<\/strong> (This model needs at least 32GB) \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/vram-guide-en\/\">VRAM quick reference<\/a><\/li>\n<li><strong>Explore the same model family<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/model-ricursiveai-ripple-en\/\">Ripple family overview (1 articles, 2 converted builds)<\/a><\/li>\n<li><strong>What Q2_K, Q4_K_M, Q8_0 mean and where to get this model<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/format-gguf-en\/\">GGUF format guide and models<\/a> \/ <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/format-fp4-en\/\">NVFP4 \/ MXFP4 format guide and models<\/a> \/ <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/glossary-quantization-en\/\">Quantization and model-format glossary<\/a><\/li>\n<li><strong>How to read Terminal-Bench, MMLU, MMLU-Pro<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/glossary-benchmarks-en\/\">Benchmark glossary<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:next-steps --><\/p>\n<h2>Sources<\/h2>\n<ul>\n<li><a href=\"https:\/\/huggingface.co\/ricursiveAI\/Ripple-65B-Preview\">ricursiveAI\/Ripple-65B-Preview<\/a><\/li>\n<li><a href=\"https:\/\/www.ricursive.com\/ripple\">Ripple-65B Preview: U.S. Open-Weight SOTA on Agentic Coding<\/a><\/li>\n<\/ul>\n<p><!-- lmw:updates --><\/p>\n<h2>Update History<\/h2>\n<ul>\n<li>2026-11-17: Added converted builds to \u201cQuantized and Converted Variants\u201d: ricursiveAI\/Ripple-65B-Preview-NVFP4, DevQuasar\/ricursiveAI.Ripple-65B-Preview-GGUF<\/li>\n<li>2026-11-17: Updated the hardware requirements table with the actual file sizes of DevQuasar\/ricursiveAI.Ripple-65B-Preview-GGUF.<\/li>\n<li>2026-11-17: Changed the title to show what the article covers (VRAM requirements, file list, etc.).<\/li>\n<\/ul>\n<p><!-- \/lmw:updates --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Ricursive Intelligence has released Ripple-65B Preview, a 65B dense model supporting a 1M context length and trained on 12 trillion tokens.<\/p>\n","protected":false},"author":1,"featured_media":17065,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[310],"tags":[4585,4587,4589,4591,1547,377,4593,4595],"class_list":["post-15137","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-new-models","tag-ricursive-intelligence-en","tag-ricursiveai-en","tag-ripple-en","tag-ripple-65b-en","tag-verified","tag--en"],"lang":"en","translations":{"en":15137,"ja":15135},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/15137","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/types\/post"}],"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=15137"}],"version-history":[{"count":5,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/15137\/revisions"}],"predecessor-version":[{"id":18050,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/15137\/revisions\/18050"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media\/17065"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=15137"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/categories?post=15137"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/tags?post=15137"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}