{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Cloud Foundry Weekly","title":"One Model to Rule Them All: Qwen3.5 122B on a Homelab for CF Agents | CF Weekly #85","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/2772b425\"></iframe>","width":"100%","height":180,"duration":4438,"description":"Originally aired live on March 6, 2026.\nFour RTX 3090s and a homelab: this week we explore running Qwen3.5-122B-A10B locally with vLLM and putting it to work for Cloud Foundry agents.\nTopics include GPTQ Int4 quantization, the moe_wna16 setting, OpenCode, and connecting the model to a BOSH-deployed OpenClaw instance. We explore how local models fit into developer and platform engineering workflows, alongside the practical trade-offs of homelab hardware and cloud subscriptions.\nThis podcast edition replaces the livestream countdown with our recorded introduction. The full closing conversation and original sign-off are preserved, followed by our podcast outro.\nWatch the video for the hardware, configuration and on-screen demonstrations\nCloud Foundry Weekly: episodes and links\nCloud Foundry Weekly hosts: Nick Kuhn, Nicky Pike, Darin Zook, and Keith Lee.","thumbnail_url":"https://img.transistorcdn.com/Lsghzwu9T0U59zIzKvHVy7j7w0AxN-XNE3Go3p7D05U/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS8xMTI5/NjEzOGY4ZTIwN2Yw/NjZkMjNhOTlkYWNl/YWU1ZS5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}