Rendered at 22:57:20 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
danw1979 3 hours ago [-]
How is this easier than using lmstudio or omlx or whatever your favourite runtime is ?
It’s maybe a bit interesting that Jetbrains are making moves to integrate with local models more closely, but I think claiming this is “easier” is incorrect for most users.
The company also said that it chose Qwen3.6 over the newer Qwen3.8 (released earlier this month) because the latter runs slower on "today's Macs" since it needs reasoning enabled.
1 hours ago [-]
satvikpendem 1 hours ago [-]
But that's incorrect, reasoning can be disabled via the template.
iAMkenough 2 hours ago [-]
I haven’t found that to be true with LM Studio and Qwen3.8. Works fine without reasoning.
They’re also targeting 64GB M5 Pro and up as “today’s Macs” which perform fine with reasoning enabled.
bellowsgulch 2 hours ago [-]
It seems to me that Qwen3.6-35B-A3B is still the local LLM leader, because 27B in either of the latest releases is just too slow to be usable compared to OpenCode Zen free models, or OpenRouter free models.
Sad a Qwen3.8-35B-A3B model wasn't released.
Also, I think this is just an ad.
coder-pm 3 hours ago [-]
Anything good to run on Mac M5 Max with 48GB? is this even worth trying? so far I found the responses so slow compared to the paid subscriptions...
seanmcdirmid 2 hours ago [-]
I get up to 90 tokens / second with Jundot/Qwen3.6-35B-A3B-oQ6-mtp, on a M3 Max with 64GB. MoE so it is not a dense model, but that means it runs faster (also, mtp helps). It is a 30GB model, but you should be able to load it, otherwise try the 4-bit quant instead of the 6-bit quant, don't bother quanting your KV Cache (don't enable turboquant in oMLX), since that will slow you down.
I'm not sure what that means on a M5 max, definitely faster, I don't know if it really plays into the strengths of the new chip design though.
bellowsgulch 3 hours ago [-]
Uh...
brew install llama.cpp
llama serve -hf unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M
open http://127.0.0.1:8080
tiahura 2 hours ago [-]
claude> dl & config best vers of Qwen 3.8 for my system
It’s maybe a bit interesting that Jetbrains are making moves to integrate with local models more closely, but I think claiming this is “easier” is incorrect for most users.
The company also said that it chose Qwen3.6 over the newer Qwen3.8 (released earlier this month) because the latter runs slower on "today's Macs" since it needs reasoning enabled.
They’re also targeting 64GB M5 Pro and up as “today’s Macs” which perform fine with reasoning enabled.
Sad a Qwen3.8-35B-A3B model wasn't released.
Also, I think this is just an ad.
I'm not sure what that means on a M5 max, definitely faster, I don't know if it really plays into the strengths of the new chip design though.