LocalLLaMA@sh.itjust.worksEnglish · 8 days ago

Qwen3 VL support merged into llama.cpp

github.com

Qwen3 VL support merged into llama.cpp

github.com

Xylight@lemdro.id to

LocalLLaMA@sh.itjust.worksEnglish · 8 days ago

[model] add support for qwen3vl series by JJJYmmm · Pull Request #16780 · ggml-org/llama.cpp

github.com

This PR adds support for the Qwen3-VL series, including both the dense and MoE variants. The original implementation was contributed by @yairpatch and @Thireus (see #16207). @LETS-BEE also helped a...

Benchmarks look pretty good, even better than some of the text only models, make sure to take them with a grain of salt tho

Benchmarks

Qwen3 VL 30b a3b (No Thinking)

Visual benchmarks for Qwen3 VL 235 A22B (Thinking)

Chat

petey@aussie.zone
link
fedilink
English
arrow-up
1·
6 days ago
I’ve been trying the 32b instruct variant at Q4_K_M and it’s been solid for general use, tool use, and image comprehension. Pretty impressive

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.

3 users / day
75 users / week
347 users / month
1.39K users / 6 months
20 local subscribers
3.83K subscribers
426 Posts
2.34K Comments
Modlog