Viewing profile — mgsram
mgsram
HN member- Joined
- Sat, Feb 15, 2025, 6:16 AM UTC
- HN karma
- 3
- Public activity
- 2 items
- HN profile
- View on Hacker News ↗
About mgsram
No profile information was provided.
Recent public activity
-
comment
Comment #48551219
I have tried plenty of other models with full FP32 as wel. However, in terms of balance between accuracy and speed, I found the Qwen 3.6 27B to be the sweet spot.
-
comment
Comment #48547933
I have been using local LLMs for about a year and I have settled now on Qwen3.6 27b dense model in GGUF on Mac Studio with 512G of RAM with open code as the harness and llmster(LM …