{"id":11689,"date":"2026-11-17T11:00:25","date_gmt":"2026-11-17T02:00:25","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/?p=11689"},"modified":"2026-11-17T11:09:38","modified_gmt":"2026-11-17T02:09:38","slug":"minicpm-v-4-7-35b-a3b-dspark-gguf-2","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/minicpm-v-4-7-35b-a3b-dspark-gguf-2\/","title":{"rendered":"MiniCPM-V-4.7-35B-A3B-DSpark-gguf Draft Model for Speedup: 4GB+ 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\/openbmb\/MiniCPM-V-4.7-35B-A3B-DSpark-gguf\">openbmb\/MiniCPM-V-4.7-35B-A3B-DSpark-gguf<\/a><\/td>\n<\/tr>\n<tr>\n<td>Family guide<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/model-openbmb-minicpm-v-4-7-dspark-en\/\">MiniCPM-V-4.7-DSpark guide (2 articles)<\/a><\/td>\n<\/tr>\n<tr>\n<td>Publisher guide<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/publisher-openbmb-en\/\">OpenBMB: models and licenses<\/a><\/td>\n<\/tr>\n<tr>\n<td>Published<\/td>\n<td>2026-10-15<\/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-gguf-en\/\">GGUF<\/a><\/td>\n<\/tr>\n<tr>\n<td>Paper<\/td>\n<td><a href=\"https:\/\/arxiv.org\/abs\/2607.05147\">arXiv:2607.05147<\/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>OpenBMB has released a GGUF (llama.cpp) quantized version of <code>MiniCPM-V-4.7-35B-A3B-DSpark<\/code>. This is not a standalone generative model, but a &#8220;speculative decoding&#8221; draft model designed to accelerate inference for the vision-language model <code>MiniCPM-V-4.7-35B-A3B<\/code>. When running <code>MiniCPM-V-4.7-35B-A3B<\/code> in llama.cpp or vLLM, simply adding this DSpark model is expected to improve response speeds.<\/p>\n<p>According to the abstract of the paper &#8220;DSpark&#8221; referenced by the model card, DSpark is a speculative decoding method that combines the high throughput of parallel draft generation with adaptive verification based on load conditions. It is described as optimizing serving efficiency by maintaining dependency between tokens via a semi-autoregressive architecture to prevent draft quality degradation, while dynamically adjusting verification lengths according to confidence scores.<\/p>\n<h2>Specifications<\/h2>\n<ul>\n<li>Architecture: <code>Qwen3DSparkModel<\/code> (<code>qwen3<\/code> family)<\/li>\n<li>Draft parameter count: 389,223,169 (approx. 390M)<\/li>\n<li>Draft layers: 5<\/li>\n<li>Draft tokens per forward pass: 15<\/li>\n<li>Target model hidden state reference layers: <code>[3, 11, 19, 27, 35]<\/code><\/li>\n<li>Checkpoint precision: BF16<\/li>\n<li>Paired target model: <code>MiniCPM-V-4.7-35B-A3B<\/code> (no specific dense\/MoE designation mentioned for the base model)<\/li>\n<\/ul>\n<h2>Performance<\/h2>\n<p>1<\/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>Domain<\/th>\n<th>Accept Length<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td><strong>Vision<\/strong><\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>MMMU<\/td>\n<td>5.098<\/td>\n<\/tr>\n<tr>\n<td>MathVista<\/td>\n<td>6.126<\/td>\n<\/tr>\n<tr>\n<td>CharXiv_reasoning_val<\/td>\n<td>5.479<\/td>\n<\/tr>\n<tr>\n<td>OCRBench<\/td>\n<td>5.407<\/td>\n<\/tr>\n<tr>\n<td><strong>Text<\/strong><\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>Math<\/td>\n<td>6.687<\/td>\n<\/tr>\n<tr>\n<td>Code<\/td>\n<td>7.387<\/td>\n<\/tr>\n<tr>\n<td>General<\/td>\n<td>3.501<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>For text domains, <code>Code<\/code> is the highest across all categories at 7.387, suggesting that tasks with predictable patterns like code generation yield higher draft acceptance rates. On the other hand, <code>General<\/code> is the lowest at 3.501, indicating that acceptance lengths are harder to extend in free-form general response generation. In the vision domain, MathVista, which measures mathematical problems involving figures and graphs in images, scored the highest at 6.126, while MMMU, which tests college-level image understanding, resulted in a relatively low 5.098. OCRBench, which measures text recognition in images, stands at 5.407, placing it in the middle among the four vision categories. Overall, the table shows a trend where inputs with easily determinable structures, such as code and mathematical formulas, yield larger speedup effects, whereas free-form general dialogue sees somewhat more modest gains.<\/p>\n<h2>Strengths and Use Cases<\/h2>\n<p>This model is a dedicated speculative decoding draft model designed to be combined with the multimodal model <code>MiniCPM-V-4.7-35B-A3B<\/code> to accelerate inference. Rather than acting as a standalone generative model for independent conversation or image recognition, it plays the role of pre-reading and proposing token sequences generated by the target model. According to the model card, quantization of the draft model has absolutely no effect on the content of the final generated output itself, influencing only the accept length (the number of tokens accepted per step).<\/p>\n<p>The target model and this draft model are tagged with <code>vision-understanding<\/code>, <code>tool-calling<\/code>, <code>conversational<\/code>, <code>en<\/code>, <code>zh<\/code>, <code>on-device<\/code>, and <code>edge-ai<\/code>. From this, the main use cases are accelerating English and Chinese text generation, conversation, tool calling, and general vision tasks accompanied by image inputs.<\/p>\n<p>As shown in the aforementioned accept length data, it achieves high accept lengths particularly in tasks requiring structured outputs such as code generation and mathematical reasoning, and is greatly expected to improve speeds in programming assistance and calculation\/logical thinking tasks. Furthermore, in image understanding tasks, stable accept lengths have been reported in MathVista (which solves graphs and geometric problems) and OCRBench (text recognition), making it well-suited for accelerating workflows involving visual reasoning and document image reading. The model is designed with edge environments and on-device deployment in mind, making it suitable for environments where response performance needs to be enhanced under limited computational resources.<\/p>\n<p><!-- lmw:hardware --><\/p>\n<h2>Hardware Requirements<\/h2>\n<p><strong>Estimated requirements (calculated by Local Model Watch)<\/strong> \u2014 389M parameters (taken from the base model openbmb\/MiniCPM-V-4.7-35B-A3B-DSpark)<\/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>4GB (laptop iGPU \/ phone class)<\/td>\n<td>F16<\/td>\n<td>0.7GB<\/td>\n<td>0.9GB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\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. 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><strong>Runs in Ollama, LM Studio and llama.cpp as-is.<\/strong><\/p>\n<p>It is distributed in GGUF, so no conversion is needed.<\/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><em>Compiled by this site&#8217;s code from the published formats, converted builds we have found, and each engine&#8217;s own model registry. &#8220;Not found&#8221; means we have not seen such a build, not that none exists. 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<p><!-- lmw:peers --><\/p>\n<h2>Recent Models in the Same Size Class<\/h2>\n<p><em>Models with <\/em><em>up to 4B<\/em><em> parameters that Local Model Watch covered recently, listed by code from our article log for comparison. VRAM tiers are this site&#8217;s estimates; licenses are as stated on the model cards.<\/em><\/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>Model<\/th>\n<th>Parameters<\/th>\n<th>Smallest VRAM tier<\/th>\n<th>License<\/th>\n<th>Our article<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>openbmb\/MiniCPM-V-4.7-1B-DSpark-gguf<\/td>\n<td>214M<\/td>\n<td>4GB<\/td>\n<td>apache-2.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/minicpm-v-4-7-1b-dspark-gguf-released\/\">MiniCPM-V-4.7-1B-DSpark-gguf Text Generation Model: 4GB+ VRAM<\/a> (2026-11-17)<\/td>\n<\/tr>\n<tr>\n<td>IFM\/Jais-3-0.9B-GGUF<\/td>\n<td>1.1B<\/td>\n<td>4GB<\/td>\n<td>apache-2.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/jais-3-0-9b-gguf-released\/\">Jais-3-0.9B-GGUF Bilingual Dense Model: 4GB+ VRAM<\/a> (2026-11-17)<\/td>\n<\/tr>\n<tr>\n<td>nvidia\/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16<\/td>\n<td>4.0B<\/td>\n<td>4GB<\/td>\n<td>openmdw-1.1<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/nvidia-dory-1-0-4b-recurrent-llm\/\">NVIDIA Releases Dory1.0-4B: A Recurrent 4B LLM with Dynamic Loops<\/a> (2026-11-17)<\/td>\n<\/tr>\n<tr>\n<td>LiquidAI\/LFM2.5-24B-A2B-DSpark<\/td>\n<td>328M<\/td>\n<td>4GB<\/td>\n<td>lfm1.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/liquid-ai-lfm25-24b-a2b-dspark\/\">LFM2.5-24B-A2B-DSpark Speculative Decoding Draft Model: 4GB+ VRAM<\/a> (2026-11-17)<\/td>\n<\/tr>\n<tr>\n<td>LiquidAI\/LFM2.5-24B-A2B-DSpark-GGUF<\/td>\n<td>328M<\/td>\n<td>4GB<\/td>\n<td>lfm1.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/liquidai-lfm2-5-24b-a2b-dspark-gguf\/\">LFM2.5-24B-A2B-DSpark-GGUF Text Generation Model: 4GB+ VRAM<\/a> (2026-11-17)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><!-- \/lmw:peers --><\/p>\n<h2>How to Get It<\/h2>\n<p>This model is distributed in GGUF format and can be obtained from the Hugging Face repository. Since it is not a gated model, it can be downloaded directly without prior application or consent procedures. Supported inference engines include <code>llama.cpp<\/code> and <code>vLLM<\/code>.<\/p>\n<p>When using it with <code>llama.cpp<\/code>, download the GGUF file of the target model itself, the vision projector (<code>mmproj<\/code>), and the GGUF file of this DSpark draft model. The model card provides the following download example using <code>huggingface-cli<\/code>:<\/p>\n<pre><code class=\"language-bash\">huggingface-cli download openbmb\/MiniCPM-V-4.7-35B-A3B-gguf MiniCPM-V-4_7-35B-A3B-Q4_K_M.gguf mmproj-model-f16.gguf --local-dir.\/35B-A3B-gguf\nhuggingface-cli download openbmb\/MiniCPM-V-4.7-35B-A3B-DSpark-gguf dspark-MiniCPM-V-4_7-35B-A3B-Q8_0.gguf --local-dir.\/35B-A3B-gguf\n<\/code><\/pre>\n<p>Using the model requires a build of <code>llama.cpp<\/code> that supports the <code>dflash<\/code> architecture and the DSpark Markov head. When running <code>llama-cli<\/code>, specify the draft model with the <code>-md<\/code> option and enable speculative decoding by specifying <code>--spec-type draft-dspark<\/code>. An example command to run it with an image and prompt via the CLI tool is as follows:<\/p>\n<pre><code class=\"language-bash\">llama-cli \\\n  -m.\/35B-A3B-gguf\/MiniCPM-V-4_7-35B-A3B-Q4_K_M.gguf \\\n  --mmproj.\/35B-A3B-gguf\/mmproj-model-f16.gguf \\\n  -md.\/35B-A3B-gguf\/dspark-MiniCPM-V-4_7-35B-A3B-Q8_0.gguf \\\n  --spec-type draft-dspark \\\n  --image image.jpg -p &quot;Describe this image.&quot; \\\n  -ngl 99 -ngld 99 -fa on -c 8192\n<\/code><\/pre>\n<p>When launching as a server, configure <code>llama-server<\/code> by passing parameters such as <code>--spec-draft-n-max 15<\/code>:<\/p>\n<pre><code class=\"language-bash\">llama-server \\\n  -m.\/35B-A3B-gguf\/MiniCPM-V-4_7-35B-A3B-Q4_K_M.gguf \\\n  --mmproj.\/35B-A3B-gguf\/mmproj-model-f16.gguf \\\n  -md.\/35B-A3B-gguf\/dspark-MiniCPM-V-4_7-35B-A3B-Q8_0.gguf \\\n  --spec-type draft-dspark --spec-draft-n-max 15 \\\n  -ngl 99 -ngld 99 -fa on -c 8192 --jinja --port 8080\n<\/code><\/pre>\n<p>Additionally, when serving with vLLM, a configuration is provided to incorporate this DSpark model via <code>--speculative-config<\/code> targeting the original BF16 checkpoint:<\/p>\n<pre><code class=\"language-bash\">vllm serve \\\n  --model openbmb\/MiniCPM-V-4.7-35B-A3B \\\n  --served-model-name MiniCPM-V-4.7-35B-A3B \\\n  --tensor-parallel-size 2 \\\n  --max-model-len 40960 \\\n  --max-num-batched-tokens 40960 \\\n  --max-num-seqs 1 \\\n  --attention-backend FLASH_ATTN \\\n  --mm-encoder-attn-backend FLASH_ATTN \\\n  --mm-processor-kwargs '{&quot;downsample_mode&quot;:&quot;4x&quot;}' \\\n  --trust-request-mm-kwargs \\\n  --disable-custom-all-reduce \\\n  --compilation-config '{&quot;pass_config&quot;:{&quot;fuse_allreduce_rms&quot;:false}}' \\\n  --speculative-config '{&quot;method&quot;:&quot;dspark&quot;,&quot;model&quot;:&quot;openbmb\/MiniCPM-V-4.7-35B-A3B-DSpark&quot;,&quot;num_speculative_tokens&quot;:15,&quot;enable_adaptive_verification&quot;:false}' \\\n  --default-chat-template-kwargs '{&quot;enable_thinking&quot;:false}'\n<\/code><\/pre>\n<p>The model card mentions that for the draft&#8217;s quantization type, one should choose the smallest one that fits into the environment, with <code>Q8_0<\/code> and <code>Q6_K<\/code> serving as good default choices.<\/p>\n<p><!-- lmw:related --><\/p>\n<h2>Related Articles<\/h2>\n<ul>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/minicpm-v-4-7-1b-dspark-gguf-released\/\">MiniCPM-V-4.7-1B-DSpark-gguf Text Generation Model: 4GB+ VRAM<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/openbmb-releases-quantized-minicpm-ocr-jev\/\">OpenBMB Releases Quantized Versions of MiniCPM-OCR-Jev<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/minicpm-ocr-1-0-dspark-overview\/\">MiniCPM-OCR-1.0-DSpark OCR Acceleration Draft Model: 4GB+ VRAM<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/08\/minicpm5-2b-released\/\">MiniCPM5-2B Text Generation Model: Our Test Answers, 4GB+ VRAM<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:related --><\/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 runs from the 4GB tier) \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/vram-guide-8gb-en\/\">Other models that run on a 8GB GPU<\/a><\/li>\n<li><strong>Explore the same model family<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/model-openbmb-minicpm-v-4-7-dspark-en\/\">MiniCPM-V-4.7-DSpark family overview (2 articles)<\/a><\/li>\n<li><strong>Engines that run this model<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-llama-cpp-en\/\">llama.cpp<\/a> \/ <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-ollama-en\/\">Ollama<\/a><\/li>\n<li><strong>Formats this model is available in<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/format-gguf-en\/\">GGUF format guide and models<\/a><\/li>\n<li><strong>Learn about the publisher<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/publisher-openbmb-en\/\">OpenBMB: models, licenses and articles<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:next-steps --><\/p>\n<h2>Sources<\/h2>\n<ul>\n<li><a href=\"https:\/\/huggingface.co\/openbmb\/MiniCPM-V-4.7-35B-A3B-DSpark-gguf\">openbmb\/MiniCPM-V-4.7-35B-A3B-DSpark-gguf (Hugging Face)<\/a><\/li>\n<li><a href=\"https:\/\/huggingface.co\/openbmb\/MiniCPM-V-4.7-35B-A3B-DSpark\">openbmb\/MiniCPM-V-4.7-35B-A3B-DSpark (Hugging Face)<\/a><\/li>\n<li><a href=\"https:\/\/arxiv.org\/abs\/2607.05147\">DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation (arXiv)<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>A GGUF quantized version of MiniCPM-V-4.7-35B-A3B-DSpark has been released by OpenBMB for speculative decoding acceleration.<\/p>\n","protected":false},"author":1,"featured_media":11688,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[310],"tags":[163,1073,3376,3378,3380,320,1547,592,1555],"class_list":["post-11689","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-new-models","tag-gguf-en","tag-llama-cpp-en","tag-minicpm-en","tag-minicpm-v-4-7-35b-a3b-en","tag-minicpm-v-4-7-dspark-en","tag-openbmb-en","tag-verified","tag-vllm-en","tag--en"],"lang":"en","translations":{"en":11689,"ja":11687},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/11689","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=11689"}],"version-history":[{"count":2,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/11689\/revisions"}],"predecessor-version":[{"id":17785,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/11689\/revisions\/17785"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media\/11688"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=11689"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/categories?post=11689"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/tags?post=11689"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}