harmony
XcodeBenchmark
| harmony | XcodeBenchmark | |
|---|---|---|
| 3 | 64 | |
| 3,642 | 3,467 | |
| - | 1.1% | |
| 3.3 | 7.7 | |
| 16 days ago | 21 days ago | |
| Rust | Swift | |
| Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
harmony
-
Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs
> GPT-OSS is not much of a snowflake
Yeah, according to the architecture it doesn't seem like a snowflake, but they also decided to invent a new prompting/conversation format (https://github.com/openai/harmony) which definitely makes it a bit of a snowflake today, can't just use what worked a couple of days ago, but everyone needs to add proper support for it.
-
OpenAI Open Models
What a day! Models aside, the Harmony Response Format[1] also seems pretty interesting and I wonder how much of an impact it might have in performance of these models.
[1] https://github.com/openai/harmony
- OpenAI Harmony
XcodeBenchmark
- OpenAI Open Models
- XcodeBenchmark: Measure the compilation time of a large codebase on Macs
- 2023 Mac Mini 10 Core M2 Pro – A Beast for Xcode Compilation
-
Who is the M3 Max for?
I’m a software developer as well and I ended up ordering a m3 max (still not received though). Main reasons against the m3 pro was the lesser number of performance cores compared to previous gens and slower memory bandwidth. Indeed, in this Xcode benchmark used by the Max Tech channel, the m3 pro compiled code slightly slower than the M1 Pro. Probably is a corner case but I think it’s worth to mention.
- Recommended mac hardware for optimal Xcode build speed
- I made a Mac Mini shopping guide, including monitor recommendations
-
14" M2 Pro vs Air M2 for C++/Rust dev
I found only one reasonable benchmark comparing compilation speed for large projects here. Does anyone have experience with these 2 machines for backend development with compiled languages?
-
[MacBook Pro 16 M2 Max 32GB 1T] or [16” M2 pro 16GB 1T + iPad Pro M2 12.9”]
Here's repo you should look at when buying a MacBook. Difference between M2 Pro and M2 Max is ~15%.
-
Mac Mini m2 vs Mac Mini M2 Pro
I'm not sure about AI/ML dataset training performance, but this XcodeBenchmark performance appears to be very comparable between the M2 and M2 Pro.
- M2 Pro vs M1 - Any proper difference?
What are some alternatives?
gpt-oss - gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
AndroidStudioBenchmark - Firefox Focus: The privacy browser - Browse like no one’s watching.
talk_to_gpt_oss - A voice agent with gpt-oss as the LLM
Gorgonia - Gorgonia is a library that helps facilitate machine learning in Go.
Pelicans-consortium
Hackintosh-13900k-Z690-AORUS-ELITE-AX-DDR5-AMD-6900XT - Hackintosh OpenCore EFI for a 100% stable Intel 13900k + Z690 AORUS ELITE AX DDR5 + AMD 6900XT + AMD RX550