I recently picked up an AMD Radeon Pro V340L for $93 CAD and successfully got both GPUs running LLM inference under Windows 11 using Vulkan and llama.cpp.

The V340L is a dual-GPU enterprise accelerator with 16 GB of HBM2 memory split between 2 GPUs. While it wasn't designed for Windows 11 desktop use, I've validated a working configuration that allows both GPUs to run inference simultaneously.

Getting It Working

The key was using AMD PRO Edition 22.Q4 with a modified driver INF to support the V340L's PCI device revision.

The V340L-Enablement project provides tooling to prepare the driver. On my Windows 11 installation, I temporarily disabled driver signature enforcement and installed the modified driver manually (you can sign the driver to avoid this.)

Both GPUs were then recognized by Windows and detected by llama.cpp's Vulkan backend.

One important configuration for llama.cpp was required to achieve usable performance:

set GGML_VK_DISABLE_HOST_VISIBLE_VIDMEM=1

This avoids a slow Vulkan memory allocation path and made a substantial difference in inference performance. 

Performance

Using Qwen3-4B Q4_K_M, I ran two independent llama.cpp inference benchmarks simultaneously, one on each GPU.

Each GPU delivered about 44.2 tokens/sec during simultaneous text generation, with virtually identical performance.

These results represent two concurrent inference workloads, rather than a single model distributed across both GPUs.

What's Next?

For less than $100 CAD, I've now got a working dual-GPU Vulkan inference setup under Windows 11, without modifying any firmware.

Next up is integrating the V340L into LLM Controller Pro, with each GPU operating as an independent inference worker.

Resources:

• V340L-Enablement
• AMD PRO Edition 22.Q4
• llama.cpp

Rasberry™ Hosting is officially live!

After 17 years of running web hosting services in one form or another, Rasberry™ is the next evolution of that work: a cleaner platform, a better customer experience, and a more focused foundation for what comes next.

I’ve built and run the infrastructure myself, backed by the same proven track record that has kept my hosting services online for the past 17 years.

The first public offering is Ubuntu VPS hosting in Canada, with static IPs included and more services planned as the platform grows.

This is not my first step into hosting, it’s the start of Rasberry™ becoming its own modern hosting platform!

Check it out:
https://rasberry.ca/

After more than 16 months of development, I'm excited to finally release LLM Controller Community Edition (CE) v1.0 as open-source software.

LLM Controller CE is a self-hosted, local-first web application for running and managing GGUF language models through llama-server It combines conversations, model management, runtime control, benchmarking, GPU monitoring, live logs, installation, and administration into a single browser interface.

The goal was never to build just another chat interface. I wanted local AI to feel like a complete product that you can install, manage, and use on hardware you control.

LLM Controller CE has been validated on both Windows and Ubuntu Linux, supports NVIDIA and AMD GPU environments where compatible tooling is available, and is released under the GPLv3 open-source license.

This has been one of the largest software projects I've built, and I'm incredibly happy to finally share it.

I hope you enjoy using it as much as I enjoyed building it!

Rasberry™ Hosting is currently undergoing infrastructure work while the static IP setup is converted to a routed subnet.

Downtime is already in effect and is expected to last until at least Friday evening.

This is a major step forward for Rasberry™.

The upgrade improves routing, infrastructure control, hosting flexibility, and future service expansion - including our first full public subnet. 🌐

Rasberry™ is steadily becoming a real hosting platform!

More soon.