Uploaded September 2026 | Updated November 2026, 3 hours ago
What can you do with a 192GB AI workstation? Watch the MINISFORUM MS-S1 MAX-P495 run a community-optimized Qwen3.8-Flash-Next 125B model locally, averaging over 40 tokens per second in this test.
🛒 Build your next local AI setup:
🇺🇸 US Store: https://s.minisforum.com/460vn59
🇪🇺 EU Store: https://s.minisforum.com/4x8loFV
🇬🇧 UK Store: https://s.minisforum.com/4gRau1e
🇫🇷 FR Store: https://s.minisforum.com/4zL2YNU
Tested configuration:
• Processor: AMD Ryzen™ AI Max+ PRO 495
• Graphics: AMD Radeon™ 8065S
• Unified Memory: 192GB LPDDR5X
• Operating System: Linux
• Model: Community-optimized Qwen3.8-Flash-Next
• Inference Engine: Halogen
From downloading the model and launching a local inference API to generating Python code, this video demonstrates the workflow on a single workstation. Watch the streaming output, server logs, and GPU activity as the model tackles a practical coding task.
Model used:
[huggingface.co/peonist-ai/halogen-qwen3.8-flash-next](https://huggingface.co/peonist-ai/halogen-qwen3.8-flash-next)
What would you run on yours?
#MINISFORUM #MSS1MAXP495 #LocalAI #AIWorkstation #Qwen
What can you do with a 192GB AI workstation? Watch the MINISFORUM MS-S1 MAX-P495 run a community-optimized Qwen3.8-Flash-Next 125B model locally, averaging over 40 tokens per second in this test.
🛒 Build your next local AI setup:
🇺🇸 US Store: https://s.minisforum.com/460vn59
🇪🇺 EU Store: https://s.minisforum.com/4x8loFV
🇬🇧 UK Store: https://s.minisforum.com/4gRau1e
🇫🇷 FR Store: https://s.minisforum.com/4zL2YNU
Tested configuration:
• Processor: AMD Ryzen™ AI Max+ PRO 495
• Graphics: AMD Radeon™ 8065S
• Unified Memory: 192GB LPDDR5X
• Operating System: Linux
• Model: Community-optimized Qwen3.8-Flash-Next
• Inference Engine: Halogen
From downloading the model and launching a local inference API to generating Python code, this video demonstrates the workflow on a single workstation. Watch the streaming output, server logs, and GPU activity as the model tackles a practical coding task.
Model used:
[huggingface.co/peonist-ai/halogen-qwen3.8-flash-next](https://huggingface.co/peonist-ai/halogen-qwen3.8-flash-next)
What would you run on yours?
#MINISFORUM #MSS1MAXP495 #LocalAI #AIWorkstation #Qwen










