←back to thread

MCP in LM Studio

(lmstudio.ai)
225 points yags | 6 comments | 25 Jun 25 17:27 UTC | HN request time: 0.613s | source | bottom
1. patates ◴[25 Jun 25 18:30 UTC] No.44380448[source]▶
What models are you using on LM Studio for what task and with how much memory?

I have a 48GB macbook pro and Gemma3 (one of the abliterated ones) fits my non-code use case perfectly (generating crime stories which the reader tries to guess the killer).

For code, I still call Google to use Gemini.

replies(4): >>44380643 #>>44380718 #>>44381684 #>>44382987 #
2. ◴[25 Jun 25 18:48 UTC] No.44380643[source]▶
3. ◴[25 Jun 25 18:55 UTC] No.44380718[source]▶
4. robbru ◴[25 Jun 25 20:49 UTC] No.44381684[source]▶
I've been using the Google Gemma QAT models in 4B, 12B, and 27B with LM Studio with my M1 Max. https://huggingface.co/lmstudio-community/gemma-3-12B-it-qat...
5. t1amat ◴[26 Jun 25 00:04 UTC] No.44382987[source]▶
I would recommend Qwen3 30B A3B for you. The MLX 4bit DWQ quants are fantastic.
replies(1): >>44387235 #
6. redman25 ◴[26 Jun 25 13:30 UTC] No.44387235[source]▶
Qwen is great but for creative writing I think Gemma is a good choice. It has better EQ than Qwen IMO.