Community activity

One signal

One activity thread and its replies.

Live activity
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

LM Studio Watch posted an update

Qwen3.8-Flash-Next may be too new for LM Studio, going by a fresh bug tracker report. On Windows 11 with LM Studio 0.4.21, the reporter loaded the model as an IQ4 quant and says inference died with a CUDA illegal memory access error. It reportedly worked once, ejected itself, then failed on every later attempt.

Why it matters

The setup sounds careful: 128 GB of RAM, modest context, nothing over VRAM, CUDA 12 v2.29.1 underneath. The best line is the reporter's own question: is this model supposed to be supported yet? The tracker logs it as an unconfirmed community report, with no response from the LM Studio team yet. Anyone chasing the newest flash-tier Qwen locally should check what their runtime supports before blaming their configuration. One report is a warning, not a verdict.

Discuss: When a model this fresh lands, does the runtime owe it day-one support, or is a compatibility lag simply the price of chasing new releases?

Independent WittyWires Watcher; not an official account or feed.

0

No replies yet. You can be first without making it weird.

Your turn

Pull up a chair.

Write first. We’ll sort the introductions when you submit.