Qwen 3.6 27B is the sweet spot for local development
1–10 of 809 posts
Re: Qwen 3.6 27B is the sweet spot for local development
#2This is kind of like saying grass is green to be honest
Re: Qwen 3.6 27B is the sweet spot for local development
#3I've come from the future to say Qwen 3.7 27B is just around the corner and slaps!
Re: Qwen 3.6 27B is the sweet spot for local development
#4And AI companies will continue to buy up all the silicon to make this prohibitively expensive to run at home.
Re: Qwen 3.6 27B is the sweet spot for local development
#5I've come from the future to say Qwen 3.7 27B is just around the corner and slaps!
Do no give me hope like that.
Re: Qwen 3.6 27B is the sweet spot for local development
#6Spent a week trying to get sensible results out of llama 3.3 At one point it even simulated doing the work, log output and everything and when I challenged it about the missing artefacts it actually started questioning my intelligence. Seems appropriate for a Zuck enterprise.
Qwen on the other hand got straight to work with astonishing competency on the same system.
From what I read llama3 needs beefier compute to reliably invoke tools, which I presume relates to it focussing more on simulating AGI rather than being a useful tool.
Re: Qwen 3.6 27B is the sweet spot for local development
#7Spent a week trying to get sensible results out of llama 3.3 At one point it even simulated doing the work, log output and everything and when I challenged it about the missing artefacts it actually started questioning my intelligence. Seems appropriate for a Zuck enterprise. Qwen on the other hand got straight to work with astonishing competency on the same system. From what I read llama3 needs beefier compute to re…
llama 3? Are you from 2023?
Re: Qwen 3.6 27B is the sweet spot for local development
#8And AI companies will continue to buy up all the silicon to make this prohibitively expensive to run at home.
It will run (somewhat slowly) on a five year old M1 Max with 64GB RAM.
Personally I prefer the 35B MoE model, which is fast enough to be interactively useful, and capable, but I would probably use the 27B if I wanted to generate whole applications like that.
I am unconvinced that most "local" AI applications need anything much more powerful than the Gemma 4 12B model. Local agentic coding is a small niche, but there are plenty of ways a local model can help with development tasks.
I would really like to see a 12B or 16B Qwen 3.6.
I am currently playing with Ornith 1.0 in the MoE configuration, which is based on the 35B variant of Qwen 3.5; I am not sure if it is better than the 3.6 version.
Benchmarks say it is; my own silly tests either suggest otherwise or suggest that I have to talk to it a bit differently.
Re: Qwen 3.6 27B is the sweet spot for local development
#9I have been having pretty good success with Qwen 3.5 9B for "nontrivial but not challenging work all things considered" -- it runs great on my 24gb unified memory m4 pro MacBook Pro. What do the baseline specs look like Mac-wise for getting this model to run? Am I looking at a 96gb? 128? 256?
Re: Qwen 3.6 27B is the sweet spot for local development
#10Spent a week trying to get sensible results out of llama 3.3 At one point it even simulated doing the work, log output and everything and when I challenged it about the missing artefacts it actually started questioning my intelligence. Seems appropriate for a Zuck enterprise. Qwen on the other hand got straight to work with astonishing competency on the same system. From what I read llama3 needs beefier compute to re…
You might find this helpful. llama is not anywhere near the Pareto distribution (performance vs cost)
https://arena.ai/leaderboard/code/webdev/pareto?license=open...
https://arena.ai/leaderboard/text/pareto?license=open-source