123
https://qwen.ai/blog?id=qwen3.8
The model weights will be open-sourced on Hugging Face and ModelScope next week — stay tuned.
I'm hoping they also release a new 35b a3b, for us VRAM poors, a new 9b would also be great!
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 03 Aug 2026
123 points (93.6% liked)
LocalLLaMA
5007 readers
42 users here now
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.
founded 3 years ago
MODERATORS
i have a 6700xt with 12gb vram. i need a usable model. 9b is barly usable because of token speed. But non the less i'm exited
Save us PrismML, you're our only hope!
https://huggingface.co/prism-ml/Bonsai-27B-gguf
With which quantization ? I have a 16GB GPU, running Qwen3.5 9b UD_Q8_K_XL basically max out the VRAM usage. Maybe a MOE model fits you. Gemma 4 e4b is one with a total 8b.
And what is the token speed you are getting ?
How much CPU RAM do you have?
At 12GB you should be using a sparse MoE with offloaded experts. There are a few to choose from, but it just depends on how much spare RAM you have.
I only have 8gb vram and can run 35b-a3b perfectly (30+ tps), have you tried 35b?
The setup described in this Codacus video is what got me started getting over 100k context with decent speeds on my RTX 3070 that I’ve been using daily for the last month: https://m.youtube.com/watch?v=0AqpaFm11oI.
The TheTom fork of llama.cpp adds asymmetric TurboQuant support that allows k at tq4 and v at tq2, which allows squeezing in more KV cache without quality loss. The REAP version of the MoE model also works just fine while further reducing the model size.
The TheTom fork doesn’t have pre-built container images, so it’s necessary to build your own (the ROCm Dockerfile in the devops directory).
If anyone does want to use the fork, I just recently built the ROCm image myself and ran into an issue where the fork’s Dockerfile was pulling a UI build package from Huggingface that doesn’t exist anymore, so I swapped in the latest ROCm Dockerfile from upstream that now builds the UI from source, and that worked fine.
Yeah do what these guys are suggesting and do the MOE with the experts offset. It really works well.
have you tried Qwen 3.6 35b a3b? check my guide, it's still relevant to you just with different numbers because you have 12GB
https://lemmus.org/post/24235317