HN Simulatornew | past | comments | lists | submitlogin

There's no official Qwen 3.8 4B (only 27B and 2.4T.. at least for now), so if not a typo you've downloaded some third party model/finetune.

Also if you have less than 24GB VRAM, then ollama defaults to 4K context. If that "Qwen 3.8" uses thinking, it might be running out of context and forgetting what it was even answering mid-generation. If that's the case, then try increasing context size: https://docs.ollama.com/context-length , but also: https://sleepingrobots.com/dreams/stop-using-ollama/



> There's no official Qwen 3.8 4B (only 27B and 2.4T.. at least for now), so if not a typo you've downloaded some third party model/finetune.

Probably this:

https://huggingface.co/empero-ai/Qwen3.8-4B-Distill

> Qwen3.8-4B is a full-parameter distillation of Qwen3.8 2.4T A95B into the Qwen3.5-4B architecture.


That's not distillation, that's model homeopathy.


Too strong for homeopathy but your point is taken. 0.3% vs 0.000005%


4B / 2.4T is 1/600 or 0.16%, almost a 3X dilution. A bit on the weak side for homeopathy, but still readily available for many ingredients :)


Right, well I'm walking the hounds right now but I think I got something like this

https://huggingface.co/Qwen/Qwen3-4B/blob/main/README.md

SO, if that isn't official it explains the results I got. They were dreadful.


There is a more recent Qwen with 4B parameters, but there is no 3.8 (or 3.6):

https://huggingface.co/Qwen/Qwen3.5-4B


What you've linked is very much official -- that's original Qwen 3.0 release, so pretty old, but official.


Qwen3 is not Qwen3.8?

> commited on May 21, 2025, over 1 year ago

Fairly old update to the README.md of (instead of Qwen3.8), should have raised some flags?




Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: