Looking for advice on a low-end AI coding setup that keeps timing out (Radeon VII + RX 5500 XT)

A home file server with 24GB of VRAM using a Radeon VII and RX 5500 XT is failing to complete large AI coding tasks, with models timing out or truncating responses. The user, nfriedly, has tried multiple harnesses including pi, Open WebUI, Open Claw, and Open Code, but only pi with muse-glimmer succeeded partially, and even that failed on a third session. The issue persists despite increasing max_completion_tokens to 128k, and the user is seeking advice on a low-end AI coding setup that can run unattended.

Hi, I have a home file server that is mostly just leftover parts + extra hard drives. I’m trying to get to a point where I can give it a task for one of my open source projects and check back in on it a day or so later to see what it’s accomplished. Or maybe have it open a pull request when it’s done. The problem is that most model + harness combos I’ve tried seem to be timing out or hitting other errors. This is the full server specs https://pcpartpicker.com/user/nfriedly/saved/XkKCD3 - it’s mostly leftover parts + extra hard drives, but it does have 24gb vram, which ought to be able to run most of these models: ollama list NAME ID SIZE MODIFIED hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q8 K XL b002f560a9a2 39 GB 6 hours ago hf.co/JonathanColetti/Qwen3.8-27B-Uncensored-GGUF:IQ4 XS 49d2e81026ce 15 GB 2 days ago gemma4:latest c6eb396dbd59 9.6 GB 4 days ago hf.co/JonathanColetti/Qwen3.8-27B-Uncensored-GGUF:Q6 K 79b2ee0918f7 22 GB 8 days ago muse-glimmer:30b de878ce33ad8 18 GB 8 days ago hf.co/unsloth/Qwen3.6-27B-GGUF:Q6 K 9bcf9b6496ac 23 GB 8 days ago hf.co/unsloth/Qwen3.6-27B-GGUF:Q3 K M b0fa9f8afbca 14 GB 8 days ago hf.co/unsloth/Qwen3.6-27B-GGUF:IQ4 XS 57c0a9428046 16 GB 8 days ago hf.co/unsloth/Qwen3.6-27B-GGUF:UD-Q4 K XL d4ddf6641ed2 18 GB 10 days ago These all work fine for basic things like “tell me a joke”, but when I give it a larger task like reviewing the changes in this PR https://github.com/nfriedly/node-unblocker/pull/307 , most of the setups I’ve tried have either hit an error or just stopped before finishing. The one success I’ve had was pi + muse glimmer: over the course of 2 sessions, it was able to first write a plan to a markdown file, and then follow through with the plan and give me a list of findings. However, in the third session, where I asked it to fix the problems it found, it too hit errors, first spinning in a loop of trying to read past the end of a file 3 times before giving up and stopping, and then finally the dreaded “Response was truncated before completion.” Once that happens in a session, it will keep happening, with the model only able to get out a few sentences, or sometimes only a few words. I tried several more models in pi with the plan that muse-glimmer created, but none of them could even finish the review. In pi, I got the error “Response was truncated before completion." after most other models worked for a bit. Pi stops with "Response was truncated before completion." · Issue 7855 · earendil-works/pi · GitHub https://github.com/earendil-works/pi/issues/7855 suggested bumping up the max completion tokens, but I got it up to 128k and it was still hitting the error well before getting to that many tokens. I’ve also tried Open WebUI + Open Terminal, but gave up when I realized that it stops working as soon as the connection breaks - I want to be able to let my laptop go to sleep and have the server keep working. Additionally I tried Open Claw, but any time I give it a larger task, it seems to just stop after a while with no apparent error. Oh, and I tried Open Code, but it mostly just blows up with too much context before even starting or, when I make a modelfile with a larger context, it spends most of it’s time compacting and never gets around to actually processing my prompt. I watched it go through 3 compactions before getting anywhere, and then gave up on it. The server is running unraid, with everything else in docker images. The models are run in ollama in vulkan mode rocm used to work with the radeon vii, but they dropped support somewhere along the line, and I don’t think the 5500 xt was ever supported. I know this is all old hardware, and the 5500 XT is dragging the Radeon VII down to a quarter of the speed it could run at on it’s own I’m getting 3~5t/s on muse-glimmer , but I feel like it ought to be able to keep going slowly, and I’m just not sure where it’s failing. Do you all have any advice for me?