{"id":11241,"date":"2026-11-17T10:59:56","date_gmt":"2026-11-17T01:59:56","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/?p=11241"},"modified":"2026-11-17T11:09:14","modified_gmt":"2026-11-17T02:09:14","slug":"weekly-news-2026-10-06","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/weekly-news-2026-10-06\/","title":{"rendered":"Weekly Open-Weight Model News: llama.cpp v0.6.0, FastH3, Beam 501B"},"content":{"rendered":"<p><!-- lmw:weekly-stats --><\/p>\n<h2>This Week in Numbers<\/h2>\n<p><em>Counted by Local Model Watch from the articles published this week.<\/em><\/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>Item<\/th>\n<th>Count<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Articles published<\/td>\n<td>8<\/td>\n<\/tr>\n<tr>\n<td>\u3000Engines and Tools<\/td>\n<td>4<\/td>\n<\/tr>\n<tr>\n<td>\u3000Image, Video and Audio<\/td>\n<td>2<\/td>\n<\/tr>\n<tr>\n<td>\u3000New Models<\/td>\n<td>1<\/td>\n<\/tr>\n<tr>\n<td>\u3000Community<\/td>\n<td>1<\/td>\n<\/tr>\n<tr>\n<td>New models covered<\/td>\n<td>3<\/td>\n<\/tr>\n<tr>\n<td>Converted builds appended to earlier articles<\/td>\n<td>7 (GGUF 4, NVFP4 1, FP8 2)<\/td>\n<\/tr>\n<tr>\n<td>Most active publishers<\/td>\n<td>fastvideo (2), vllm-project\/vllm (1), naiveai (1)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<h3>Trending models we did not cover separately<\/h3>\n<p><em>Hugging Face repositories that trended this week but did not get their own article. Listed for reference; we have not reviewed their model cards.<\/em><\/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>Model<\/th>\n<th>Likes<\/th>\n<th>Downloads<\/th>\n<th>Why no article<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td><a href=\"https:\/\/huggingface.co\/autotrust\/GLM5.3-Flash-E224-DGX-Spark\">autotrust\/GLM5.3-Flash-E224-DGX-Spark<\/a><\/td>\n<td>556<\/td>\n<td>11,534<\/td>\n<td>converted build without a parent article<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/huggingface.co\/ConwayResearch\/Underdog-Saluki-27B-1.0\">ConwayResearch\/Underdog-Saluki-27B-1.0<\/a><\/td>\n<td>322<\/td>\n<td>108,900<\/td>\n<td>publisher not on our notable list<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/huggingface.co\/bartowski\/K2-Horizon-7B-GGUF\">bartowski\/K2-Horizon-7B-GGUF<\/a><\/td>\n<td>0<\/td>\n<td>2,004<\/td>\n<td>converted build without a parent article<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/huggingface.co\/bartowski\/K2-Horizon-32B-GGUF\">bartowski\/K2-Horizon-32B-GGUF<\/a><\/td>\n<td>0<\/td>\n<td>3,831<\/td>\n<td>converted build without a parent article<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<h3>Patch releases we did not cover separately<\/h3>\n<p><em>Releases of watched projects that were patch-level or had short notes. Each project&#8217;s page lists every version.<\/em><\/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>Project<\/th>\n<th>Version<\/th>\n<th>Release notes<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>ollama\/ollama<\/td>\n<td>v0.40.1<\/td>\n<td><a href=\"https:\/\/github.com\/ollama\/ollama\/releases\/tag\/v0.40.1\">GitHub<\/a><\/td>\n<\/tr>\n<tr>\n<td>ollama\/ollama<\/td>\n<td>v0.40.3<\/td>\n<td><a href=\"https:\/\/github.com\/ollama\/ollama\/releases\/tag\/v0.40.3\">GitHub<\/a><\/td>\n<\/tr>\n<tr>\n<td>turboderp-org\/exllamav3<\/td>\n<td>v1.6.1<\/td>\n<td><a href=\"https:\/\/github.com\/turboderp-org\/exllamav3\/releases\/tag\/v1.6.1\">GitHub<\/a><\/td>\n<\/tr>\n<tr>\n<td>unslothai\/unsloth<\/td>\n<td>v0.1.904-beta<\/td>\n<td><a href=\"https:\/\/github.com\/unslothai\/unsloth\/releases\/tag\/v0.1.904-beta\">GitHub<\/a><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<h3>Models Gaining the Most Likes<\/h3>\n<p><em>Compiled by Local Model Watch from weekly snapshots of models we&#8217;ve covered. Likes are cumulative on Hugging Face; downloads are its trailing-30-day count.<\/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>Likes gained<\/th>\n<th>Total likes<\/th>\n<th>Downloads (30d)<\/th>\n<th>Period<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td><a href=\"https:\/\/huggingface.co\/Cloudflare\/clef\">Cloudflare\/clef<\/a><\/td>\n<td>+820<\/td>\n<td>2,028<\/td>\n<td>14,351<\/td>\n<td>2026-W41 \u2192 2026-W42<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/huggingface.co\/Qwen\/Qwen3.8-27B\">Qwen\/Qwen3.8-27B<\/a><\/td>\n<td>+569<\/td>\n<td>17,508<\/td>\n<td>6,843,108<\/td>\n<td>2026-W41 \u2192 2026-W42<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/huggingface.co\/Cloudflare\/clef-flash\">Cloudflare\/clef-flash<\/a><\/td>\n<td>+330<\/td>\n<td>756<\/td>\n<td>22,123<\/td>\n<td>2026-W41 \u2192 2026-W42<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/huggingface.co\/deepseek-ai\/DeepSeek-V4.1-Flash\">deepseek-ai\/DeepSeek-V4.1-Flash<\/a><\/td>\n<td>+271<\/td>\n<td>4,364<\/td>\n<td>1,382,367<\/td>\n<td>2026-W41 \u2192 2026-W42<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/huggingface.co\/prism-ml\/Ternary-Bonsai-2-27B-gguf\">prism-ml\/Ternary-Bonsai-2-27B-gguf<\/a><\/td>\n<td>+214<\/td>\n<td>2,630<\/td>\n<td>4,549,911<\/td>\n<td>2026-W41 \u2192 2026-W42<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><!-- \/lmw:weekly-stats --><\/p>\n<h2>Highlights of the Week<\/h2>\n<p>This week saw a series of major and minor updates to key inference engines and foundational libraries supporting local inference. Additionally, developments such as inference efficiency improvements in the video generation sector and community announcements of massive open-weight models directly impacted execution speeds and model choices on local hardware.<\/p>\n<p>First is the simultaneous update of inference engines and foundational libraries. Releases include <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/10\/06\/llama-cpp-v0-6-0-released\/\">llama.cpp v0.6.0 Released: New Batch API, Metal Speedups, and New Model Support<\/a>, <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/10\/06\/ggml-v0-26-0-released\/\">Inference Foundation Library &#8220;ggml v0.26.0&#8221; Released with Backend Optimizations and Expanded Support<\/a>, <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/10\/05\/vllm-v0-31-0-released\/\">Inference Engine vllm v0.31.0 Released with Fast Restarts and DeepSeek Optimizations<\/a>, and <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/10\/06\/magnitude-cli-0-2-6-released\/\">Inference Engine &#8220;magnitude&#8221; v0.2.6 Released with Major Speedups for Prompt Processing on Mac<\/a>. Ongoing optimizations for Metal and various backends are raising processing performance in local environments.<\/p>\n<p>Second is the progress in step reduction and low-bit quantization for the audio-visual generation model &#8220;FastH3&#8221;. Updates include the release of <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/10\/06\/fasth3-trim-8-step\/\">Audio-Visual Video Generation Model &#8220;FastH3 Trim&#8221; 8-Step Version Released<\/a> as well as <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/10\/06\/fasth3-v2-fp8-nvfp4-released\/\">Audio-Visual Video Generation Model &#8220;FastH3 V2&#8221; FP8 and NVFP4 Versions Released<\/a>. Practical approaches for running computationally heavy video generation on local GPUs are rapidly falling into place.<\/p>\n<p>Third is the announcement of a massive open-weight model reaching a total of 501B parameters. <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/10\/06\/beam-reflection-501b-open-weight-model\/\">Reflection Announces Open-Weight Model &#8220;Beam&#8221; with 501B Total Parameters<\/a> has drawn attention as a large-scale MoE model rollout originating from the community.<\/p>\n<h2>Trends by Category<\/h2>\n<h3>Engines and Tools<\/h3>\n<p>The most active area this week was engines and tools. Across multiple projects, hardware optimization\u2014particularly speeding up Apple Silicon (Metal) environments and adding new features\u2014became a shared focus.<\/p>\n<p><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/10\/06\/llama-cpp-v0-6-0-released\/\">llama.cpp v0.6.0 Released: New Batch API, Metal Speedups, and New Model Support<\/a> introduced a new batch API and tuned Metal environments, while its foundation, <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/10\/06\/ggml-v0-26-0-released\/\">Inference Foundation Library &#8220;ggml v0.26.0&#8221; Released with Backend Optimizations and Expanded Support<\/a>, enhanced Vulkan, WebGPU, and Apple Silicon backends. Furthermore, the Rust-based engine <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/10\/06\/magnitude-cli-0-2-6-released\/\">Inference Engine &#8220;magnitude&#8221; v0.2.6 Released with Major Speedups for Prompt Processing on Mac<\/a> improved prompt processing speeds on Mac, bringing heavily beneficial updates for users leveraging Macs as local inference environments.<\/p>\n<p>Meanwhile, for server-side and Linux tools, <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/10\/05\/vllm-v0-31-0-released\/\">Inference Engine vllm v0.31.0 Released with Fast Restarts and DeepSeek Optimizations<\/a> incorporated fast restart capabilities, DeepSeek optimizations, and Blackwell support, advancing efficient inference infrastructure.<\/p>\n<h3>Image, Video, and Audio<\/h3>\n<p>In media generation, practical speedups and memory reductions for audio-visual video generation models emerged as a clear trend.<\/p>\n<p>Driven by FastVideo, <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/10\/06\/fasth3-trim-8-step\/\">Audio-Visual Video Generation Model &#8220;FastH3 Trim&#8221; 8-Step Version Released<\/a> enabled video generation with fewer inference steps. Combined with <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/10\/06\/fasth3-v2-fp8-nvfp4-released\/\">Audio-Visual Video Generation Model &#8220;FastH3 V2&#8221; FP8 and NVFP4 Versions Released<\/a>, efficient execution environments utilizing next-generation low-bit representations have been provided. While video generation is notoriously heavy to run on local machines, algorithmic step reduction and memory-reducing quantization are rapidly driving optimization forward.<\/p>\n<h3>Text Generation and Community<\/h3>\n<p>In text generation and community trends, developments surrounding large-scale Mixture of Experts (MoE) models stood out.<\/p>\n<p>From the community, <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/10\/06\/beam-reflection-501b-open-weight-model\/\">Reflection Announces Open-Weight Model &#8220;Beam&#8221; with 501B Total Parameters<\/a> announced the availability of an exceptionally large open-weight model. Additionally, among articles covered on our site this week, the previously released AI research and coding MoE model <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/10\/05\/naive-n05-flash\/\">&#8220;Naive-N0.5-Flash&#8221; MoE Model for AI Research and Coding: Approx. 690GB Required Memory<\/a> was featured. As the presence of large-scale MoE models grows, the importance of quantization and distributed environments for running them locally is being rediscovered.<\/p>\n<h2>Industry Movements<\/h2>\n<p>Announcements from companies and research institutions that were not made into individual articles because they are not topics for local execution. Only the key points are included.<\/p>\n<ul>\n<li><strong>Allen Institute for AI<\/strong>: The Allen Institute for AI (Ai2) participated in COLM 2026, sharing open research initiatives regarding the development of models, data, and scientific AI agent tools. (<a href=\"https:\/\/allenai.org\/blog\/colm-2026-recap\">Announcement<\/a>)<\/li>\n<li><strong>Hugging Face Blog<\/strong>: NVIDIA&#8217;s research team announced a method that fine-tunes the Nemotron model family to achieve gold medal-level performance in both the International Olympiad in Informatics (IOI) and the International Mathematical Olympiad (IMO). (<a href=\"https:\/\/huggingface.co\/blog\/nvidia\/nemotron-ioi-and-imo-2026\">Announcement<\/a>)<\/li>\n<li><strong>Together AI<\/strong>: Together AI announced a partnership with IBM Cloud and NVIDIA to launch a large-scale inference cluster on IBM Cloud using NVIDIA B300 GPUs and Spectrum-X Ethernet networking. (<a href=\"https:\/\/www.together.ai\/blog\/expanding-our-enterprise-inference-capacity-with-ibm-cloud-and-nvidia\">Announcement<\/a>)<\/li>\n<li><strong>datasocial<\/strong>: datasocial released a dataset named &#8220;tiktok-5.6B-videos&#8221;, containing captions and statistical information for 5,597,462,038 public TikTok videos from 2014 through October 2026. (<a href=\"https:\/\/huggingface.co\/datasets\/datasocial\/tiktok-5.6B-videos\">Announcement<\/a>)<\/li>\n<\/ul>\n<p><!-- lmw:related --><\/p>\n<h2>Related Articles<\/h2>\n<ul>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/ramalama-v0260-released-2\/\">RamaLama v0.26.0 Released: TLS Support and GPU Detection Updates<\/a><\/li>\n<li><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><\/li>\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\/minicpm-v-4-7-35b-a3b-dspark-gguf-2\/\">MiniCPM-V-4.7-35B-A3B-DSpark-gguf Draft Model for Speedup: 4GB+ VRAM<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:related --><\/p>\n<p><!-- lmw:weekly-articles --><\/p>\n<h2>This Week&#8217;s Articles<\/h2>\n<p><em>Compiled by Local Model Watch from the article log. Articles about the same story are merged into one row.<\/em><\/p>\n<h3>New Models<\/h3>\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>Date<\/th>\n<th>Model<\/th>\n<th>Params<\/th>\n<th>Smallest VRAM tier<\/th>\n<th>License<\/th>\n<th>Converted builds<\/th>\n<th>Article<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>2026-10-05<\/td>\n<td>NaiveAI\/Naive-N0.5-Flash<\/td>\n<td>\u2014<\/td>\n<td>\u2014<\/td>\n<td>mit<\/td>\n<td>2<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/05\/naive-n05-flash-released\/\">Naive-N0.5-Flash MoE Model for AI Research and Coding: ~690GB Memory<\/a><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<h3>Image, Video and Audio<\/h3>\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>Date<\/th>\n<th>Model<\/th>\n<th>Params<\/th>\n<th>Smallest VRAM tier<\/th>\n<th>License<\/th>\n<th>Converted builds<\/th>\n<th>Article<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>2026-10-06<\/td>\n<td>FastVideo\/FastVideo-FastH3-Trim-8-Step-NVFP4<\/td>\n<td>\u2014<\/td>\n<td>\u2014<\/td>\n<td>other<\/td>\n<td>\u2014<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/06\/fasth3-trim-8-step-video-generation-model\/\">FastH3 Trim: 8-Step Text-to-Video Model with Audio Support<\/a> (follow-up: <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/06\/fasth3-v2-quantized-models-released\/\">Two Quantized Versions of Audio-Visual Video Generation Model FastH<\/a>)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<h3>Engines and Tools<\/h3>\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>Date<\/th>\n<th>Project<\/th>\n<th>Version<\/th>\n<th>Article<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>2026-10-06<\/td>\n<td>magnitudedev\/magnitude<\/td>\n<td>@magnitudedev\/cli@0.2.6<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/06\/magnitudedev-magnitude-026-released\/\">magnitudedev\/magnitude v0.2.6 Released: Major Mac Speedups<\/a><\/td>\n<\/tr>\n<tr>\n<td>2026-10-06<\/td>\n<td>ggml-org\/llama.cpp<\/td>\n<td>v0.6.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/06\/llamacpp-v0-6-0-released\/\">llama.cpp v0.6.0 Released with llama_batch_ext and Metal Boosts<\/a><\/td>\n<\/tr>\n<tr>\n<td>2026-10-06<\/td>\n<td>ggml-org\/ggml<\/td>\n<td>v0.26.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/06\/ggml-v0260-released\/\">ggml v0.26.0 Released with Sparse Flash Attention &amp; New Backends<\/a><\/td>\n<\/tr>\n<tr>\n<td>2026-10-05<\/td>\n<td>vllm-project\/vllm<\/td>\n<td>v0.31.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/05\/vllm-v0310-released\/\">vLLM v0.31.0 Released: Fast Restart and Hardware Optimization<\/a><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<h3>Community<\/h3>\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>Date<\/th>\n<th>Article<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>2026-10-06<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/06\/reflection-announces-beam-open-weight-moe-model\/\">Reflection Announces Beam: A 501B Open-Weight MoE Model<\/a><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><!-- \/lmw:weekly-articles --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Catch up on the latest open-weight generative model news, including major updates to llama.cpp v0.6.0, FastH3 video generation, and the 501B Beam model.<\/p>\n","protected":false},"author":1,"featured_media":11240,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[159],"tags":[3049,3037,163,1073,165,1547,592],"class_list":["post-11241","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-weekly-roundup","tag-beam-en","tag-fasth3-en","tag-gguf-en","tag-llama-cpp-en","tag-moe-en","tag-verified","tag-vllm-en"],"lang":"en","translations":{"en":11241,"ja":11239},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/11241","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=11241"}],"version-history":[{"count":2,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/11241\/revisions"}],"predecessor-version":[{"id":17745,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/11241\/revisions\/17745"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media\/11240"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=11241"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/categories?post=11241"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/tags?post=11241"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}