deleted by creator

I didn’t know it has ads. I used it to avoid sending a direct link to Twitter.

I assume it’s to simplify the review process. Or to generate more hype. Or both.

They announced that it would be released next week, so I doubt they’ve only just started training it.

There will be Flash, 27B and 2 other models called Plus and Max.

They most likely used a local fork for a while.

I heard some people use adaptive kv streaming to fit large contexts. Unfortunately, it’s not merged into the upstream yet.

Interesting, I had the opposite experience. Especially for tool calls. But I heard it depends on the use case: Qwen better at coding and tool calls, Gemma is better for prose.

I’d recommend to try Qwen Flash Next with such hardware. You should have just enough RAM. Even Q3 should be quite good.

You can also try https://huggingface.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF

It’s more demanding, but also much capable.

I personally run Qwen 3.8 27B at Q4_K_XL, but given OP’s system requirements, I’d try Bonsai instead of a regular Q2 quant or the older Qwen 3.5 9B.

Try Ternary Bonsai. It’s a heavily quantized version of Qwen 3.8 27b. It won’t do wonders, but it shoud be better: https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf-dev The page says you need a fork of llama.cpp, but the support was included in the latest release (0.7). You can read more about the mode on the main model page: https://huggingface.co/prism-ml/Ternary-Bonsai-27B-gguf

Cool!

I hope the upcoming 1.0 release will attract some new active users.

Yes, I always toggle fast forward on loading screens!

I’m so used to this that sometimes I even instinctively try to toggle it on in non-emulated games 😅