PolyStrata: Strata fork with support for more MoE models: Qwen3.8-Flash-Next, GLM 5.3 Flash, Qwen3.6, Ornith 1.5 and Gemma 4

github.com

PolyStrata: Strata fork with support for more MoE models: Qwen3.8-Flash-Next, GLM 5.3 Flash, Qwen3.6, Ornith 1.5 and Gemma 4

github.com

BeefAndPoultry@lemmus.org to

LocalLLaMA@sh.itjust.worksEnglish · 15 days ago

GitHub - VecSzn/PolyStrata: Run large AI models on your own PC: Qwen3.8-Flash-Next, GLM 5.3 Flash, Qwen3.6, Ornith 1.5 and Gemma 4. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost, image input. Built on Strata.

github.com

Run large AI models on your own PC: Qwen3.8-Flash-Next, GLM 5.3 Flash, Qwen3.6, Ornith 1.5 and Gemma 4. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost, image input. Buil...

It’s a fork of Strata to add support for more models

I haven’t tried this, and it definitely looks vibecoded, but the benchmarks look good

Qwen3.6-35B-A3B

NVIDIA: RTX 4070 Laptop (8 GB), Core i7-14700HX, 32 GB RAM

Size	Writes answers	Reads your prompt
UD-Q3_K_M	73-75 tokens/s	1,390 tokens/s
UD-Q2_K_XL	91 tokens/s	1,320 tokens/s
UD-Q4_K_M	58-61 tokens/s	1,100-1,350 tokens/s

Gemma 4 26B-A4B

NVIDIA: RTX 4070 Laptop (8 GB), Core i7-14700HX, 32 GB RAM

Size	Writes answers	Reads your prompt
UD-Q3_K_M	70-71 tokens/s	1,910 tokens/s
UD-Q2_K_XL	86-87 tokens/s	1,840 tokens/s
UD-Q4_K_M	67 tokens/s	1,840 tokens/s

You must log in or register to comment.

Chat

LocalLLaMA@sh.itjust.works

localllama@sh.itjust.works

Create a post

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !localllama@sh.itjust.works

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

Rules:

Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.

Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.

Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they’re still using the same algorithms since <over 10 years ago>.

Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

23 users / day
172 users / week
598 users / month
708 users / 6 months
1 local subscriber
5.38K subscribers
278 Posts
1.34K Comments
Modlog