Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

We tested Qwen3.8-Flash-Next on the MINISFORUM MS-S1 MAX-P495 AI Workstation, powered by AMD Ryzen™ AI Max+ PRO 495. 🤖 🚀 🛒 Learn more: 🇺🇸 US: 🇪🇺 EU: What would you like to test on it? #MINISFORUM #MSS1MAXP495 #LocalAI #AIWorkstation

Hi_MINISFORUM's profile picture

MINISFORUM Official

18,407 subscribers

11,118 görüntüleme • 15 gün önce •via X (Twitter)

#MINISFORUM#MSS1MAXP495#LocalAI
LIVE

Anya Rossi• Live Now

Private livecam show

12 Yorum

Ash Hart profil fotoğrafı
Ash Hart15 gün önce

I bet it would run faster on my TensorFold engine. I sent you a dm a week ago.

lejars gianni profil fotoğrafı
lejars gianni15 gün önce

Would love to run my Luna benchmark on it: 40 tool-calling prompts + a 24/7 local assistant test (llama.cpp ROCm). qwen3:30b-a3b scores best for me but doesn't fit in my 16GB VRAM, so 64GB+ unified memory is exactly the missing piece. I'd publish all the results. #LocalAI #MINISFORUM #AMD #ROCm #LocalLLM #AIAgents #SelfHosted

Costin Raiu profil fotoğrafı
Costin Raiu15 gün önce

so, where are the test results? 😀

Dr. D profil fotoğrafı
Dr. D14 gün önce

Way over priced

Lain // 🇷🇺 profil fotoğrafı
Lain // 🇷🇺15 gün önce

How many tokens per second? 🙃

Jims-Garage profil fotoğrafı
Jims-Garage15 gün önce

Awesome, I'm currently running it on the MS-S1 Max - the extra RAM on the 495 would be a huge improvement for quants! Looking forward to seeing it.

Dipl. Ing MkenyaDaima | Bongani | Mamba | profil fotoğrafı
Dipl. Ing MkenyaDaima | Bongani | Mamba |15 gün önce

Order it here 😍

MiniPC Guru profil fotoğrafı
MiniPC Guru15 gün önce

Flash-Next is the easy warmup for the MS-S1 MAX — the real test is a 70B at Q4 sustained. The P495 SKU's spec that matters most: up to 192GB of unified memory, with the full pool usable for weights instead of being capped at dGPU VRAM.

Momo D NH profil fotoğrafı
Momo D NH15 gün önce

Very expensive 🫰

Mike Gannotti 🔳 profil fotoğrafı
Mike Gannotti 🔳14 gün önce

🔥🔥🔥🔥

Sofi f. profil fotoğrafı
Sofi f.14 gün önce

A Ryzen AI Max+ PRO 495 with unified memory is the interesting part here, not the model. What's the actual tokens/sec and memory bandwidth once the model exceeds the shared LPDDR pool?

Aapakari profil fotoğrafı
Aapakari15 gün önce

A 30B MoE at Q4, with prompt processing reported separately

Benzer Videolar

The MINISFORUM MS-S1 MAX-P495 AI Workstation is now available to order! 🚀 Powered by the AMD Ryzen™ AI Max+ Pro 495 processor and up to 192GB of unified memory, it lets you run larger AI models locally and bring your AI projects to life on your desktop. 🛒 First batch limited to 100 units worldwide. Order yours now: 🇪🇺 EU Store: 🇺🇸 US Store: 🇫🇷 FR Store: 🇬🇧 UK Store: What would you run on yours? 🤖 #MINISFORUM #MSS1MAX #AIWorkstation #LocalAI
1:00

The MINISFORUM MS-S1 MAX-P495 AI Workstation is now available to order! 🚀 Powered by the AMD Ryzen™ AI Max+ Pro 495 processor and up to 192GB of unified memory, it lets you run larger AI models locally and bring your AI projects to life on your desktop. 🛒 First batch limited to 100 units worldwide. Order yours now: 🇪🇺 EU Store: 🇺🇸 US Store: 🇫🇷 FR Store: 🇬🇧 UK Store: What would you run on yours? 🤖 #MINISFORUM #MSS1MAX #AIWorkstation #LocalAI

MINISFORUM Official

24,822 görüntüleme • 17 gün önce

Can a $351 mini PC run a 30B+ AI model locally? 👀 We tested the MINISFORUM UM790 Pro with Qwen 35B — and the results might surprise you. 💻 Powered by: • AMD Ryzen™ 9 7940HS • Radeon™ 780M iGPU • 48GB DDR5 RAM (dual-channel) 🚀 Smooth local inference at 20+ tokens/sec (based on our test setup, results may vary) No cloud. No API fees. Just local AI. 🔒 🔗 Learn more: #MINISFORUM #UM790Pro #LocalAI #MiniPC #AI #LLM #Tech
1:21

Can a $351 mini PC run a 30B+ AI model locally? 👀 We tested the MINISFORUM UM790 Pro with Qwen 35B — and the results might surprise you. 💻 Powered by: • AMD Ryzen™ 9 7940HS • Radeon™ 780M iGPU • 48GB DDR5 RAM (dual-channel) 🚀 Smooth local inference at 20+ tokens/sec (based on our test setup, results may vary) No cloud. No API fees. Just local AI. 🔒 🔗 Learn more: #MINISFORUM #UM790Pro #LocalAI #MiniPC #AI #LLM #Tech

MINISFORUM Official

75,641 görüntüleme • 5 ay önce

Something new is coming. 👀 Meet the MINISFORUM MS-03 Workstation — a compact local AI edge workstation powered by Intel® Core™ Ultra 386H, with dual 10G SFP+, select Intel® vPro® support, up to 128GB DDR5 7200MT/s memory, and flexible M.2 + U.2 storage expansion. ✨ Subscribe now for an exclusive $50 launch coupon. 🇺🇸 US Store: 🇪🇺 EU Store: 🇯🇵 JP Store: 🇬🇧 UK Store: 🇫🇷 FR Store: 🇰🇷 KR Store: 🇦🇺 AU Store: 🇨🇦 CA Store: 🇷🇺 RU Store: Be the first to get the launch deal. Subscribe now. #MINISFORUM #MS03 #Workstation #LocalAI #EdgeAI #IntelCoreUltra #vPro #SFPPlus #MiniWorkstation
0:35

Something new is coming. 👀 Meet the MINISFORUM MS-03 Workstation — a compact local AI edge workstation powered by Intel® Core™ Ultra 386H, with dual 10G SFP+, select Intel® vPro® support, up to 128GB DDR5 7200MT/s memory, and flexible M.2 + U.2 storage expansion. ✨ Subscribe now for an exclusive $50 launch coupon. 🇺🇸 US Store: 🇪🇺 EU Store: 🇯🇵 JP Store: 🇬🇧 UK Store: 🇫🇷 FR Store: 🇰🇷 KR Store: 🇦🇺 AU Store: 🇨🇦 CA Store: 🇷🇺 RU Store: Be the first to get the launch deal. Subscribe now. #MINISFORUM #MS03 #Workstation #LocalAI #EdgeAI #IntelCoreUltra #vPro #SFPPlus #MiniWorkstation

MINISFORUM Official

19,832 görüntüleme • 3 ay önce

192GB of unified memory, up to 160GB of it for the GPU: the HP ZBook Ultra G3a 16 has the most GPU memory we've seen on an AMD Ryzen AI Max system. New 100W thermal design (55W on the G1a), 96Wh battery, Gen5 slot to 8TB, 4.2 lb. #HPZBook #LocalAI #Workstation HP Z Workstations & Solutions AMD Ryzen
2:49

192GB of unified memory, up to 160GB of it for the GPU: the HP ZBook Ultra G3a 16 has the most GPU memory we've seen on an AMD Ryzen AI Max system. New 100W thermal design (55W on the G1a), 96Wh battery, Gen5 slot to 8TB, 4.2 lb. #HPZBook #LocalAI #Workstation HP Z Workstations & Solutions AMD Ryzen

StorageReview.com

66,568 görüntüleme • 29 gün önce

One shot builds aren’t cloud only. Qwen 3.8 Flash plans the build, then hands it to Qwen 3.8 27B, all running locally across the GPU, CPU and 128GB of unified memory on one AMD Ryzen AI Max+ processor. Now, we iterate. See how Ryzen AI Max+ helps you build.
0:41

One shot builds aren’t cloud only. Qwen 3.8 Flash plans the build, then hands it to Qwen 3.8 27B, all running locally across the GPU, CPU and 128GB of unified memory on one AMD Ryzen AI Max+ processor. Now, we iterate. See how Ryzen AI Max+ helps you build.

AMD Ryzen

17,829 görüntüleme • 21 gün önce

AMD Agent Computers Power the Next Generation of Hollywood Studios Emmy-winning Light Sail VR uses private, local AI on Ryzen AI Max and Radeon AI PRO R9700, overseeing up to 9 projects all at once, leaving more time for storytelling.
1:57

AMD Agent Computers Power the Next Generation of Hollywood Studios Emmy-winning Light Sail VR uses private, local AI on Ryzen AI Max and Radeon AI PRO R9700, overseeing up to 9 projects all at once, leaving more time for storytelling.

AMD

33,226 görüntüleme • 10 gün önce

KOJIMA PRODUCTIONS × ROG Pre-order has started for our collab PC👍 An outer shell designed by Yoji Shinkawa based on the idea that it is "one of Ludens' gadgets" and incredible performance powered by AMD Ryzen™ AI MAX+ 395 and 128GB of RAM. Learn more here👉 #ForLudensWhoDare
0:30

KOJIMA PRODUCTIONS × ROG Pre-order has started for our collab PC👍 An outer shell designed by Yoji Shinkawa based on the idea that it is "one of Ludens' gadgets" and incredible performance powered by AMD Ryzen™ AI MAX+ 395 and 128GB of RAM. Learn more here👉 #ForLudensWhoDare

KOJIMA PRODUCTIONS (Eng)

46,641 görüntüleme • 7 ay önce

A guy who tested every AI Halo mini PC on the market picked a winner: The Minisforum MS-S1 Max They all run the same AMD Ryzen AI Max+ 395 with 128GB unified memory, so the decision came down to everything around the chip What won it: dual 10-gig Ethernet, 80 Gbit/s USB4 V2, internal power supply, a low-profile PCIe slot the competition skipped The overlooked detail: the CPU/GPU memory split quietly changes CPU performance by 15% on identical silicon The honest comparison: NVIDIA's GB10 boxes have nearly closed the price gap and still lead on software maturity. AMD's edge is Windows, gaming, and expansion in one machine The takeaway is not which box is fastest It is that local AI hardware is now a commodity, and the real differences are the boring ones: ports, service, and software
17:57

A guy who tested every AI Halo mini PC on the market picked a winner: The Minisforum MS-S1 Max They all run the same AMD Ryzen AI Max+ 395 with 128GB unified memory, so the decision came down to everything around the chip What won it: dual 10-gig Ethernet, 80 Gbit/s USB4 V2, internal power supply, a low-profile PCIe slot the competition skipped The overlooked detail: the CPU/GPU memory split quietly changes CPU performance by 15% on identical silicon The honest comparison: NVIDIA's GB10 boxes have nearly closed the price gap and still lead on software maturity. AMD's edge is Windows, gaming, and expansion in one machine The takeaway is not which box is fastest It is that local AI hardware is now a commodity, and the real differences are the boring ones: ports, service, and software

plutos

97,428 görüntüleme • 3 ay önce

💥AI is no longer confined to the cloud. At Computex, Jack Huynh showcased the AMD Ryzen AI Halo and Ryzen AI Max PRO 400 Series processors. The next wave of innovation will be built, trained, and run locally. As AI evolves from chatbots to intelligent agents, developers and enterprises need the performance, memory capacity, and flexibility to bring these experiences to life directly on the device. ⚡ Ryzen AI Halo enables local AI development with support for models up to 200B parameters, up to 128GB of unified memory, ROCm optimization, and Windows + Linux support. ⚡ Ryzen AI Max PRO 400 Series combines AI, graphics, and compute in a single architecture, delivering workstation-class performance for next-gen Agent Computers and AI PCs. Some of the most impactful AI experiences will happen right at your desk, where latency, privacy, and control matter most. We're just getting started.
1:24

💥AI is no longer confined to the cloud. At Computex, Jack Huynh showcased the AMD Ryzen AI Halo and Ryzen AI Max PRO 400 Series processors. The next wave of innovation will be built, trained, and run locally. As AI evolves from chatbots to intelligent agents, developers and enterprises need the performance, memory capacity, and flexibility to bring these experiences to life directly on the device. ⚡ Ryzen AI Halo enables local AI development with support for models up to 200B parameters, up to 128GB of unified memory, ROCm optimization, and Windows + Linux support. ⚡ Ryzen AI Max PRO 400 Series combines AI, graphics, and compute in a single architecture, delivering workstation-class performance for next-gen Agent Computers and AI PCs. Some of the most impactful AI experiences will happen right at your desk, where latency, privacy, and control matter most. We're just getting started.

AMD

24,416 görüntüleme • 4 ay önce

Running a 300B-parameter AI model locally on a laptop used to sound like fantasy, but HP's new ZBook Ultra G3a 16 is doing just that. 💻 Powered by AMD and up to 192GB of unified memory, this thin-and-light workstation lets you run massive LLMs and multi-agent workflows without paying cloud token costs. It even ships with Perplexity Computer tools preinstalled for app integrations like Autodesk Revit. 🤖 HP expects the laptop to be available later this month. No pricing information yet. #HPZBook #MobileWorkstation #LocalAI #AMD #Unboxing
0:24

Running a 300B-parameter AI model locally on a laptop used to sound like fantasy, but HP's new ZBook Ultra G3a 16 is doing just that. 💻 Powered by AMD and up to 192GB of unified memory, this thin-and-light workstation lets you run massive LLMs and multi-agent workflows without paying cloud token costs. It even ships with Perplexity Computer tools preinstalled for app integrations like Autodesk Revit. 🤖 HP expects the laptop to be available later this month. No pricing information yet. #HPZBook #MobileWorkstation #LocalAI #AMD #Unboxing

PCMag

41,726 görüntüleme • 6 gün önce

Go2NFT just activated AI. Game on! 🔥 The AI Fitting Room is here — try on tokenized fashion and see how it looks on you. 👗🤖 Powered by our custom-built AI. Designed to scale brands. Built to grow Go2NFT. 📲 Download the Go2NFT app. Explore the future. Own your look. Product tokenization — next level. 💪🏻🚀
0:22

Go2NFT just activated AI. Game on! 🔥 The AI Fitting Room is here — try on tokenized fashion and see how it looks on you. 👗🤖 Powered by our custom-built AI. Designed to scale brands. Built to grow Go2NFT. 📲 Download the Go2NFT app. Explore the future. Own your look. Product tokenization — next level. 💪🏻🚀

Go2NFT

249,193 görüntüleme • 1 yıl önce

BREAKING $AMD is ready to ship Ryzen AI Halo 🆕 in June 2026!!!! 🚀🚀🚀 AKA Personal/Local AI system. Ryzen AI Max+ 395 (Strix Halo APU) with 128 GB of unified LPDDR5X memory, 40 RDNA 3.5 GPU compute units, and a full ROCm software stack preloaded for both Windows and Linux. AMD Halo is $2,000-$3,000 vs $NVDA Spark $4,699 The main purpose of the AMD Ryzen AI Halo is to serve as a compact, developer focused workstation for running intensive AI workloads locally, specifically building, testing, prototyping, fine-tuning, and deploying generative AI models (like LLMs) and Agentic AI applications without relying on the cloud. Run models with up to 200 billion parameters on your desk using 128 GB of unified memory (shared across CPU, GPU, and NPU). This eliminates cloud costs, latency, data privacy concerns, and internet dependency. ~This is for AI developers, researchers, engineers, and creators. ~Teams or individuals wanting faster iteration, data privacy, and cost savings compared to cloud APIs. ~Users experimenting with open-source models, fine-tuning, inference, and production-like local deployment Source: AMD CES 2026
2:47

BREAKING $AMD is ready to ship Ryzen AI Halo 🆕 in June 2026!!!! 🚀🚀🚀 AKA Personal/Local AI system. Ryzen AI Max+ 395 (Strix Halo APU) with 128 GB of unified LPDDR5X memory, 40 RDNA 3.5 GPU compute units, and a full ROCm software stack preloaded for both Windows and Linux. AMD Halo is $2,000-$3,000 vs $NVDA Spark $4,699 The main purpose of the AMD Ryzen AI Halo is to serve as a compact, developer focused workstation for running intensive AI workloads locally, specifically building, testing, prototyping, fine-tuning, and deploying generative AI models (like LLMs) and Agentic AI applications without relying on the cloud. Run models with up to 200 billion parameters on your desk using 128 GB of unified memory (shared across CPU, GPU, and NPU). This eliminates cloud costs, latency, data privacy concerns, and internet dependency. ~This is for AI developers, researchers, engineers, and creators. ~Teams or individuals wanting faster iteration, data privacy, and cost savings compared to cloud APIs. ~Users experimenting with open-source models, fine-tuning, inference, and production-like local deployment Source: AMD CES 2026

Mike

16,097 görüntüleme • 4 ay önce

A GUY TESTED EVERY AI MINI PC SO YOU DON'T HAVE TO. The winner? Not the one most people expected. Every box used the same AMD Ryzen AI Max+ 395 chip and 128GB memory. The difference came down to the boring stuff: → Dual 10Gb Ethernet → 80 Gbit/s USB4 V2 → PCIe expansion → Better memory configuration Wild part: a simple memory split changed performance by up to 15% on the exact same silicon. Local AI hardware is becoming a commodity. The next battle isn't chips. It's ports, software, and ecosystem.
17:58

A GUY TESTED EVERY AI MINI PC SO YOU DON'T HAVE TO. The winner? Not the one most people expected. Every box used the same AMD Ryzen AI Max+ 395 chip and 128GB memory. The difference came down to the boring stuff: → Dual 10Gb Ethernet → 80 Gbit/s USB4 V2 → PCIe expansion → Better memory configuration Wild part: a simple memory split changed performance by up to 15% on the exact same silicon. Local AI hardware is becoming a commodity. The next battle isn't chips. It's ports, software, and ecosystem.

Radha Tripathi

23,648 görüntüleme • 3 ay önce

🤖 We are entering the second revolution of Personal AI. AI agents aren’t just answering questions, they’re working for you 24/7 to help you stay ahead. Imagine a virtual team that continuously processes data, monitors systems, and executes tasks automatically even while you sleep. With AMD Agent Computers, your AI agents collaborate like a virtual team, maintaining context, sharing insights, and executing tasks as part of a coordinated agentic workflow, something that wasn’t possible before. Everything runs locally, keeping your data private and secure 🛡️ They think deeply, reasoning through problems, connecting insights, and making decisions that multiply your impact. Powered by Ryzen AI Max and Radeon AI PRO, your models, context, and tools live together, no token limits, fully local and private. 💡 Experience what a 24/7 AI team can do to multiply your impact beyond what you thought possible. 🔥 Join us April 30 in San Francisco at AMD Developer Day:
3:10

🤖 We are entering the second revolution of Personal AI. AI agents aren’t just answering questions, they’re working for you 24/7 to help you stay ahead. Imagine a virtual team that continuously processes data, monitors systems, and executes tasks automatically even while you sleep. With AMD Agent Computers, your AI agents collaborate like a virtual team, maintaining context, sharing insights, and executing tasks as part of a coordinated agentic workflow, something that wasn’t possible before. Everything runs locally, keeping your data private and secure 🛡️ They think deeply, reasoning through problems, connecting insights, and making decisions that multiply your impact. Powered by Ryzen AI Max and Radeon AI PRO, your models, context, and tools live together, no token limits, fully local and private. 💡 Experience what a 24/7 AI team can do to multiply your impact beyond what you thought possible. 🔥 Join us April 30 in San Francisco at AMD Developer Day:

Jack Huynh

24,609 görüntüleme • 5 ay önce

THE MS-A2 IS THE MINISFORUM BOX HERMES AGENT WAS NEVER MEANT TO RUN ON, AND THAT'S BY DESIGN The MS-S1 MAX earns its spot running Hermes Agent because of one thing. 128GB of unified memory, up to 96GB of it handed straight to the GPU. That's the only reason a 120B model fits and runs locally for $0 a month The MS-A2 solves a different problem. Ryzen 9 9955HX, 16 cores, 32 threads, up to 96GB of regular DDR5-5600, no unified pool Three M.2 PCIe 4.0 slots, one U.2, two 22110. Dual 10Gbps SFP+ LAN plus 2.5G. WiFi 6E. Bluetooth 5.3. A slide-out motherboard for fast upgrades. A real PCIe x16 slot that actually takes a low-profile GPU That last part is where the two machines split for good. The MS-S1 MAX's PCIe slot won't take a GPU at all, every bit of GPU power has to come from the unified chip itself. The MS-A2 trades that unified memory trick for raw expandability instead One box runs a local AI agent. The other runs a home lab that needs storage, networking, and room to grow. Minisforum built both on purpose, not as the same product wearing two names
1:06

THE MS-A2 IS THE MINISFORUM BOX HERMES AGENT WAS NEVER MEANT TO RUN ON, AND THAT'S BY DESIGN The MS-S1 MAX earns its spot running Hermes Agent because of one thing. 128GB of unified memory, up to 96GB of it handed straight to the GPU. That's the only reason a 120B model fits and runs locally for $0 a month The MS-A2 solves a different problem. Ryzen 9 9955HX, 16 cores, 32 threads, up to 96GB of regular DDR5-5600, no unified pool Three M.2 PCIe 4.0 slots, one U.2, two 22110. Dual 10Gbps SFP+ LAN plus 2.5G. WiFi 6E. Bluetooth 5.3. A slide-out motherboard for fast upgrades. A real PCIe x16 slot that actually takes a low-profile GPU That last part is where the two machines split for good. The MS-S1 MAX's PCIe slot won't take a GPU at all, every bit of GPU power has to come from the unified chip itself. The MS-A2 trades that unified memory trick for raw expandability instead One box runs a local AI agent. The other runs a home lab that needs storage, networking, and room to grow. Minisforum built both on purpose, not as the same product wearing two names

NO1ennn

25,645 görüntüleme • 3 ay önce

Meet AMD Skills: A growing catalog of agent skills that helps AI coding assistants work more effectively with AMD hardware and software. Compatible with coding agents including Cursor, Claude Code, OpenAI Codex, and Gemini CLI, AMD Skills provides the knowledge, scripts, and best practices developers need to build faster on AMD. Why try it? → Install in seconds with the Skills CLI → Learn AMD best practices and workflows → Build AI applications from client to cloud → Pick only the skills you need Get started: npx skills add amd/skills Explore the project, install a skill, and let us know what you'd like to see next:
0:40

Meet AMD Skills: A growing catalog of agent skills that helps AI coding assistants work more effectively with AMD hardware and software. Compatible with coding agents including Cursor, Claude Code, OpenAI Codex, and Gemini CLI, AMD Skills provides the knowledge, scripts, and best practices developers need to build faster on AMD. Why try it? → Install in seconds with the Skills CLI → Learn AMD best practices and workflows → Build AI applications from client to cloud → Pick only the skills you need Get started: npx skills add amd/skills Explore the project, install a skill, and let us know what you'd like to see next:

AI at AMD

13,609 görüntüleme • 2 ay önce

How To Use griffain Step-by-step - What are AI agents - How to get early access - Pump fun agents explained - The new apps on the @ store Leave a comment below if you would like to learn more 👇
22:29

How To Use griffain Step-by-step - What are AI agents - How to get early access - Pump fun agents explained - The new apps on the @ store Leave a comment below if you would like to learn more 👇

Tyrelle Anderson-Brown

44,166 görüntüleme • 1 yıl önce

We are thrilled to announce Kasumi2 Open Beta 🎉🤖 Kasumi2 is an autonomous AI agent that performs actions in the Arbius network. It is a miner, has its own wallet, can retrieve results from Arbius AI models, and runs its own individual LLM model. Additionally, Kasumi2 can run any AI model for fast generations, is censorship-resistant, decentralized, and responds with AI powered interactions If you would like to test it out, click on the link below. 🔗
0:28

We are thrilled to announce Kasumi2 Open Beta 🎉🤖 Kasumi2 is an autonomous AI agent that performs actions in the Arbius network. It is a miner, has its own wallet, can retrieve results from Arbius AI models, and runs its own individual LLM model. Additionally, Kasumi2 can run any AI model for fast generations, is censorship-resistant, decentralized, and responds with AI powered interactions If you would like to test it out, click on the link below. 🔗

Arbius

25,081 görüntüleme • 2 yıl önce