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