Tried to debug a perl project I inherited using a local LLM. I have a M4 Max with 64GB. Running with opencode and often times getting stupid loops of the model trying the same thing over and over again or "Iä Iä Cthulu Ftaghn" output.
Tried GPT-OSS 20B, Qwen3.5 9B which were completely terrible. Qwen 3.6 40B was better but horribly slow.
Am I doing something wrong or are local models really this stupid?
Frederik Braun �
npub195…yx4mx
2026-07-09 06:20:37 UTC
Author Public Key
npub1958mefcsz02gs9h45vwrj7q92cjd3l0gflk2e04m7ev4ynvuzr8qayx4mxPublished at
2026-07-09 06:20:37 UTCEvent JSON
{
"id": "121dc2f1cad79d043c69051e2586538a34c7f6f7421f1f0ce9eaa6e2d0afd5a2",
"pubkey": "2d0fbca71013d48816f5a31c3978055624d8fde84fecacbebbf659524d9c10ce",
"created_at": 1783578037,
"kind": 1,
"tags": [
[
"proxy",
"https://social.security.plumbing/@freddy/116888570272909529",
"web"
],
[
"proxy",
"https://social.security.plumbing/users/freddy/statuses/116888570272909529",
"activitypub"
],
[
"L",
"pink.momostr"
],
[
"l",
"pink.momostr.activitypub:https://social.security.plumbing/users/freddy/statuses/116888570272909529",
"pink.momostr"
],
[
"-"
]
],
"content": "Tried to debug a perl project I inherited using a local LLM. I have a M4 Max with 64GB. Running with opencode and often times getting stupid loops of the model trying the same thing over and over again or \"Iä Iä Cthulu Ftaghn\" output.\n\nTried GPT-OSS 20B, Qwen3.5 9B which were completely terrible. Qwen 3.6 40B was better but horribly slow. \nAm I doing something wrong or are local models really this stupid?",
"sig": "d366ee0bb55b580812c9ea4f1968f350d9579b6059ba49ccb8599524f1281d9753b785dbf2ebfd47eb3b27a8d90360a88e0196187818b61e8e2d33fc2eb7dee4"
}