--- title: $2600 LattePanda Sigma 2 single board server features... description: The LattePanda Sigma 2 is a single board computer built around an Intel Core Ultra X7 358H Panther Lake-H chip with Arc B390 graphics and a 50 TOPS NPU,... canonical: https://daily.dev/posts/2600-lattepanda-sigma-2-single-board-server-features-180-tops-intel-core-ultra-x7-358h-soc-for-loca-pstvhdphm twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: $2600 LattePanda Sigma 2 single board server features 180 TOPS Intel Core Ultra X7 358H SoC for local AI applications | daily.dev og:description: The LattePanda Sigma 2 is a single board computer built around an Intel Core Ultra X7 358H Panther Lake-H chip with Arc B390 graphics and a 50 TOPS NPU,... og:url: https://daily.dev/posts/2600-lattepanda-sigma-2-single-board-server-features-180-tops-intel-core-ultra-x7-358h-soc-for-loca-pstvhdphm og:image: https://api.daily.dev/og/posts/PStvHdpHM.png og:image:alt: $2600 LattePanda Sigma 2 single board server features 180 TOPS Intel Core Ultra X7 358H SoC for local AI applications og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # $2600 LattePanda Sigma 2 single board server features 180 TOPS Intel Core Ultra X7 358H SoC for local AI applications **[CNX Software](https://daily.dev/sources/cnx-software)** · [@cnxsoft](https://daily.dev/cnxsoft) · 4 min read · 0 upvotes · 0 comments ## Summary The LattePanda Sigma 2 is a single board computer built around an Intel Core Ultra X7 358H Panther Lake-H chip with Arc B390 graphics and a 50 TOPS NPU, reaching 180 TOPS combined for local AI. It ships with up to 64GB of LPDDR5X-8533 RAM, three M.2 M-Key slots, an OCuLink port, two Thunderbolt 4 ports and dual 10GbE. A 1TB SSD comes pre-installed with Ubuntu 26.04, and the documentation describes OpenVINO Model Server serving the Qwen3.6-35B-A3B model locally at about 30 tokens per second, with OpenClaw on a browser dashboard. A Raspberry Pi RP2350 co-processor handles GPIO for sensors and actuators. It's up for pre-order at $2,599 through mid-November, rising to $2,799 afterward. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What TOPS performance does the Intel Core Ultra X7 358H chip deliver for local AI? The Intel Core Ultra X7 358H delivers up to 180 TOPS combined across its CPU, GPU, and NPU. The 12-core Intel Arc B390 GPU alone reaches up to 122 TOPS (INT8), while the integrated NPU contributes 50 TOPS, and the chip has an 18 MB Intel Smart Cache with a 25-watt processor base power. _Developers evaluating edge AI chips can track real-world TOPS and benchmark numbers on daily.dev._ ### How fast does a 35B parameter MoE model run on LattePanda Sigma 2 hardware? The Qwen3.6-35B-A3B INT4 model runs locally at around 30 tokens per second on the LattePanda Sigma 2. The board allocates up to 59GB of VRAM for AI workloads, giving enough headroom for 35B-class quantized mixture-of-experts models plus the KV cache needed by long-context AI agents, served through OpenVINO Model Server on an OpenAI-compatible API. _Anyone sizing local LLM hardware can compare real throughput numbers like this on daily.dev._ ### How much does the LattePanda Sigma 2 single board computer cost? The LattePanda Sigma 2 is priced at $2,599 for pre-order with 1TB SSD and 64GB RAM, available until mid-November, after which the price rises to $2,799. It includes an Intel Core Ultra X7 358H processor, 64GB LPDDR5X-8533 RAM, dual 10GbE, two Thunderbolt 4 ports, and a Raspberry Pi RP2350 GPIO co-processor. _Developers budgeting edge-AI hardware purchases can follow pricing and spec changes on daily.dev._ ## Similar posts on daily.dev - [LattePanda Mu Ultra Compute Module features Intel Core Ultra 5 226V/7 256V Lunar Lake CPU for AI workloads](https://daily.dev/posts/lattepanda-mu-ultra-compute-module-features-intel-core-ultra-5-226v-7-256v-lunar-lake-cpu-for-ai-wor-vbp4n9vqe) · CNX Software · 1 upvotes · 0 comments - [A $329 octa-core 64-bit RISC-V mini-ITX motherboard with a PCIe Gen4 x16 slot](https://daily.dev/posts/a-329-octa-core-64-bit-risc-v-mini-itx-motherboard-with-a-pcie-gen4-x16-slot-tflkdhno7) · Hacker News · 4 upvotes · 0 comments - [Orange Pi 6 CIX CD8180 12-core Arm SBC gets 2.5GbE networking, smaller form factor, drops battery support](https://daily.dev/posts/orange-pi-6-cix-cd8180-12-core-arm-sbc-gets-2-5gbe-networking-smaller-form-factor-drops-battery-su-oyuey9ljb) · CNX Software · 4 upvotes · 0 comments --- Tags: [#hardware](https://daily.dev/tags/hardware), [#npu](https://daily.dev/tags/npu) [View this post on daily.dev](https://daily.dev/posts/2600-lattepanda-sigma-2-single-board-server-features-180-tops-intel-core-ultra-x7-358h-soc-for-loca-pstvhdphm) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"$2600 LattePanda Sigma 2 single board server features 180 TOPS Intel Core Ultra X7 358H SoC for local AI applications","url":"https://daily.dev/posts/2600-lattepanda-sigma-2-single-board-server-features-180-tops-intel-core-ultra-x7-358h-soc-for-loca-pstvhdphm","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/2600-lattepanda-sigma-2-single-board-server-features-180-tops-intel-core-ultra-x7-358h-soc-for-loca-pstvhdphm"},"datePublished":"2026-10-29T09:09:26.271Z","dateModified":"2026-10-30T06:00:14.077Z","description":"The LattePanda Sigma 2 is a single board computer built around an Intel Core Ultra X7 358H Panther Lake-H chip with Arc B390 graphics and a 50 TOPS NPU,...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a36b11afd8fb595708fdd3050722a434?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a36b11afd8fb595708fdd3050722a434?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"CNX Software","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Person","name":"CNXSoft","url":"https://daily.dev/cnxsoft","image":"https://avatars.githubusercontent.com/u/1366138?v=4","interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"EndorseAction"},"userInteractionCount":550}},"commentCount":0,"discussionUrl":"https://daily.dev/posts/2600-lattepanda-sigma-2-single-board-server-features-180-tops-intel-core-ultra-x7-358h-soc-for-loca-pstvhdphm","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"hardware,npu","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"CNX Software","item":"https://daily.dev/sources/cnx-software"},{"@type":"ListItem","position":3,"name":"$2600 LattePanda Sigma 2 single board server features 180 TOPS Intel Core Ultra X7 358H SoC for local AI applications"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/2600-lattepanda-sigma-2-single-board-server-features-180-tops-intel-core-ultra-x7-358h-soc-for-loca-pstvhdphm#faq","mainEntity":[{"@type":"Question","name":"What TOPS performance does the Intel Core Ultra X7 358H chip deliver for local AI?","acceptedAnswer":{"@type":"Answer","text":"The Intel Core Ultra X7 358H delivers up to 180 TOPS combined across its CPU, GPU, and NPU. The 12-core Intel Arc B390 GPU alone reaches up to 122 TOPS (INT8), while the integrated NPU contributes 50 TOPS, and the chip has an 18 MB Intel Smart Cache with a 25-watt processor base power. Developers evaluating edge AI chips can track real-world TOPS and benchmark numbers on daily.dev."}},{"@type":"Question","name":"How fast does a 35B parameter MoE model run on LattePanda Sigma 2 hardware?","acceptedAnswer":{"@type":"Answer","text":"The Qwen3.6-35B-A3B INT4 model runs locally at around 30 tokens per second on the LattePanda Sigma 2. The board allocates up to 59GB of VRAM for AI workloads, giving enough headroom for 35B-class quantized mixture-of-experts models plus the KV cache needed by long-context AI agents, served through OpenVINO Model Server on an OpenAI-compatible API. Anyone sizing local LLM hardware can compare real throughput numbers like this on daily.dev."}},{"@type":"Question","name":"How much does the LattePanda Sigma 2 single board computer cost?","acceptedAnswer":{"@type":"Answer","text":"The LattePanda Sigma 2 is priced at $2,599 for pre-order with 1TB SSD and 64GB RAM, available until mid-November, after which the price rises to $2,799. It includes an Intel Core Ultra X7 358H processor, 64GB LPDDR5X-8533 RAM, dual 10GbE, two Thunderbolt 4 ports, and a Raspberry Pi RP2350 GPIO co-processor. Developers budgeting edge-AI hardware purchases can follow pricing and spec changes on daily.dev."}}]} ```