How to setup a local coding agent on macOS

Post by threecheese » Sat, Jun 13, 2026, 4:19 PM UTC

Phemist wrote: post #122

freerunnering wrote: post #88

Earlier quoted context omitted.

> I appreciate the author for sharing their experience, but for beginners this might not be the best guide to use. Yeah, I didn't write this as a proper developer guide. My screen recording started getting loads of favourites and I started getting messages asking about how I set it up, so just through up a quick rundown of how I setup this test. I little just saw the Unclothe announcement about "Double the speed" and…

I wasn't familiar with Unclothe, so I had to look it up.. Are you sure you did not mean Unsloth?

Post by contingencies » Sat, Jun 13, 2026, 4:26 PM UTC

spike021 wrote: post #86

contingencies wrote: post #50

Earlier quoted context omitted.

M4 24GB here. You'll be fine, if you're anything like me minor latency is acceptable to obtain (a) privacy (b) reliability (c) CI/CD/guardrails (d) network independence (e) future-proofing vs. AIaaS. https://omlx.ai/ gives you intelligent local hardware based model download recommendations. That said it probably depends heavily on your workload, process and polish expectations. See also https://news.ycombinator.com/i…

what are you using on yours? I've got a M4 Pro 24GB also. tried the open source gpt one. it's alright but I found it can get stuck at times. maybe just my config in LM Studio.

Post by anigbrowl » Sat, Jun 13, 2026, 6:39 PM UTC

freerunnering wrote: post #90

anigbrowl wrote: post #79

This video is realtime. And shows the agent responding at a perfectly usable speed. Alas, this video appears not have been linked to the text that describes it. Perhaps I should ask an AI to generate an artistic rendering of the author's description.

The video is stuck in an ` ` tag so you need to wait for it to load. On a slow connection it might just not show for a while. Though the video is only 1MB so should load in if you wait.

Post by mft_ » Sat, Jun 13, 2026, 8:11 PM UTC

smcleod wrote: post #128

mft_ wrote: post #12

Earlier quoted context omitted.

I found a marginal downside to Qwen3.6-35B-A3B-MTP vs. the non-MTP equivalent on an M1 Max. I’ll maybe experiment with settings further though.

Use the 27b, it's better in every way once you add MTP (which speeds up dense models but often doesn't add any performance to MoE models like the 35b-a3b). I get around 100TK/s on my 2x 3090 machine and 85 on my M5 Max.

Post by freerunnering » Sat, Jun 13, 2026, 11:34 PM UTC

Phemist wrote: post #122

freerunnering wrote: post #88

Earlier quoted context omitted.

> I appreciate the author for sharing their experience, but for beginners this might not be the best guide to use. Yeah, I didn't write this as a proper developer guide. My screen recording started getting loads of favourites and I started getting messages asking about how I set it up, so just through up a quick rundown of how I setup this test. I little just saw the Unclothe announcement about "Double the speed" and…

I wasn't familiar with Unclothe, so I had to look it up.. Are you sure you did not mean Unsloth?