this post was submitted on 24 Jun 2026
137 points (81.9% liked)

Selfhosted

60177 readers
511 users here now

A place to share alternatives to popular online services that can be self-hosted without giving up privacy or locking you into a service you don't control.

Rules:

Detailed Rules Post

  1. Be civil.

  2. No spam.

  3. Posts are to be related to self-hosting.

  4. Don't duplicate the full text of your blog or readme if you're providing a link.

  5. Submission headline should match the article title.

  6. No trolling.

  7. Promotion posts require active participation, with an account that is at least 30 days old. F/LOSS without a paywall has exceptions, with requirements. See the rules link for details.

Resources:

Any issues on the community? Report it using the report flag.

Questions? DM the mods!

founded 3 years ago
MODERATORS
 

Do you host your own ML / AI / LLM? What do you use, and what do you use it for?

you are viewing a single comment's thread
view the rest of the comments
[–] domi@lemmy.secnd.me 12 points 2 days ago (1 children)

Yes, I got a Strix Halo machine before the RAM price hike and use it to run all my ML stuff on it.

Currently using llama-swap with llama.cpp/ComfyUI and opencode/Open WebUI as frontend.

I'm running Qwen3.6-27b, Voxtral Mini 4b, Piper and Qwen Image. Also, some embedding and reranking models.

I use them for:

  • Tagging and classification of my documents in Paperless
  • Home Assistant (voice assistant)
  • Translations (both text and image)
  • Transcriptions
  • Some light coding and debugging
  • Avatar/Backdrop generation for DnD sessions
[–] SuspiciousCarrot78@aussie.zone 2 points 2 days ago (1 children)

What sort of tok/s are you getting on the strix?

[–] domi@lemmy.secnd.me 3 points 2 days ago (1 children)

About 200 t/s prompt processing and 10-20 t/s with MTP.

Greatly depends on the task, predictable things like code generates at 18-20 t/s. Creative writing more like 10-17 t/s.

[–] SuspiciousCarrot78@aussie.zone 2 points 2 days ago (1 children)

Damn - I thought strix would do a bit better than that, for how much it costs.

[–] robber@lemmy.ml 3 points 2 days ago (2 children)

Given the 27b is a dense model, I think the numbers are quite ok. Curious about the quant tho.

The cool thing about the strix is its large unified memory, but it lacks memory bandwith for compute intensive workloads. Something like Qwen3.5-122b MoE with only like 12b active parameters might run at twice the speed if it fits the configuration.

[–] domi@lemmy.secnd.me 1 points 2 days ago (1 children)

Curious about the quant tho.

Q8 from unsloth.

Something like Qwen3.5-122b

My go to model for knowledge. Definitely much faster at Q5 but it lacks the tool calling quality of the Qwen3.6 models. Really hoping we see a Qwen3.6-122b soon...

[–] robber@lemmy.ml 1 points 1 day ago

In case you missed the Ornith 1.0 release (Qwen and Gemma RL finetunes for agentic / coding workloads), they look interesting to bridge the gap until we see larger 3.6 models or a 3.7 release. I didn't test them yet but according to benchmarks, the 35b MoE seems to be more or less on par with Qwen3.6 27b dense, while ofc a lot faster.

[–] SuspiciousCarrot78@aussie.zone 1 points 2 days ago (1 children)

Yeah. Though I think theres a new strix out soon (Medusa? Gorgon? Something like that).

Its a bit like my P40. On paper, it has 24GB. But that 24gb is capped at 400GB/s and the ai compute is what...Pascal era?

AI = Good, fast, cheap - pick 2

[–] robber@lemmy.ml 1 points 1 day ago

Well compared to the strix, 400GB/s is not that bad, I think with fast system RAM and expert offloading you could squeeze quite something out of it when running stuff in the 100b-a10b regions.

Your bigger problem is going to be future software support.