RIriedel·Jul 13, 2026
Cool stuff. Just read: https://github.com/akandr/bc250
In Benchmarking 15 "E-Waste" GPUs with Modern Workloadsakandr
bc250
Python2026–2026
akandr / bc250
bc250
AMD BC-250 (PS5 APU) setup guide — Ollama + Vulkan inference, poor man's AI assistant via Signal, stable-diffusion.cpp image generation
2Distinct people
3Mentions
0Explicit recommenders
430GitHub stars
What to know before exploring
What it is
AMD BC-250 (PS5 APU) setup guide — Ollama + Vulkan inference, poor man's AI assistant via Signal, stable-diffusion.cpp image generation
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:03:16 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by week3 dated mentions
Observed mentions: 2026-03-17 20:49:16 UTC to 2026-07-13 18:39:03 UTC. Weeks start Monday, UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Mar 16 | 2026-03-16 00:00:00 UTC | 2026-03-23 00:00:00 UTC | 1 | 1 | 0 |
| Mar 23 | 2026-03-23 00:00:00 UTC | 2026-03-30 00:00:00 UTC | 1 | 1 | 0 |
| Mar 30 | 2026-03-30 00:00:00 UTC | 2026-04-06 00:00:00 UTC | 0 | 0 | 0 |
| Apr 6 | 2026-04-06 00:00:00 UTC | 2026-04-13 00:00:00 UTC | 0 | 0 | 0 |
| Apr 13 | 2026-04-13 00:00:00 UTC | 2026-04-20 00:00:00 UTC | 0 | 0 | 0 |
| Apr 20 | 2026-04-20 00:00:00 UTC | 2026-04-27 00:00:00 UTC | 0 | 0 | 0 |
| Apr 27 | 2026-04-27 00:00:00 UTC | 2026-05-04 00:00:00 UTC | 0 | 0 | 0 |
| May 4 | 2026-05-04 00:00:00 UTC | 2026-05-11 00:00:00 UTC | 0 | 0 | 0 |
| May 11 | 2026-05-11 00:00:00 UTC | 2026-05-18 00:00:00 UTC | 0 | 0 | 0 |
| May 18 | 2026-05-18 00:00:00 UTC | 2026-05-25 00:00:00 UTC | 0 | 0 | 0 |
| May 25 | 2026-05-25 00:00:00 UTC | 2026-06-01 00:00:00 UTC | 0 | 0 | 0 |
| Jun 1 | 2026-06-01 00:00:00 UTC | 2026-06-08 00:00:00 UTC | 0 | 0 | 0 |
| Jun 8 | 2026-06-08 00:00:00 UTC | 2026-06-15 00:00:00 UTC | 0 | 0 | 0 |
| Jun 15 | 2026-06-15 00:00:00 UTC | 2026-06-22 00:00:00 UTC | 0 | 0 | 0 |
| Jun 22 | 2026-06-22 00:00:00 UTC | 2026-06-29 00:00:00 UTC | 0 | 0 | 0 |
| Jun 29 | 2026-06-29 00:00:00 UTC | 2026-07-06 00:00:00 UTC | 0 | 0 | 0 |
| Jul 6 | 2026-07-06 00:00:00 UTC | 2026-07-13 00:00:00 UTC | 0 | 0 | 0 |
| Jul 13 | 2026-07-13 00:00:00 UTC | 2026-07-20 00:00:00 UTC | 1 | 0 | 1 |
What Hacker News says
3 sourcesShow HN: Tok/s on a 35B MoE model using a $100 AMD crypto APU and Vulkan
2 points · Open discussionShow HN: 35B MoE LLM and other models locally on an old AMD crypto APU (BC250)
Hi HN,
I put together some info on repurposing the AMD BC-250, an APU (Zen 2 + RDNA 1.5 "Cyan Skillfish") originally made for blockchain appliances. They've been showing up on AliExpress for around $150.
Since it's an unusual hybrid chip (GFX1013), I ended up running the AI compute stack entirely through Vulkan (via Mesa/RADV).
Out of the box, the Linux kernel's TTM memory manager caps allocations, causing OOMs on larger models. I found that passing ttm.pages_limit=4194304 to the kernel bypasses this and unlocks the full 16GB of Unified Memory (UMA) directly for the GPU.
With the memory unlocked, it makes for a fun piece of inference hardware. Currently it runs:
* Qwen3.5-35B-A3B MoE via Ollama at ~38 tok/s. (Interestingly, 27B dense models crash because the GPU lacks matrix cores, but the 35B MoE runs fine since only 3B parameters are ac
Read the rest
tive per token).
* FLUX.2-klein-9B for local image generation.
I documented the driver workarounds, memory settings and some benchmarks in the repo in case anyone else has one of these boards and wants to tinker with it (and not just repurpose it as poor man's GabeCube ;)).