Weekly archive
New local AI models, May 20–26, 2024
4 open models released May 20–26, 2024, with how each runs on five reference devices.
-
56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
-
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
-
38Basic quality (D) · 38 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
- Phone iPhone 17 Pro Runs well 13.4 tok/s
- Laptop MacBook Pro M5 Pro 64 GB Runs great 44.8 tok/s
- Gaming PC RTX 5090 32 GB Runs great 71.2 tok/s
- Edge board Jetson Orin NX 16 GB Runs well 17.3 tok/s
- Workstation Mac Studio 512 GB Runs great 60.8 tok/s
-
32Basic quality (D) · 32 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
- Phone iPhone 17 Pro Runs well 16.2 tok/s
- Laptop MacBook Pro M5 Pro 64 GB Runs great 41.9 tok/s
- Gaming PC RTX 5090 32 GB Runs great 66.7 tok/s
- Edge board Jetson Orin NX 16 GB Runs well 16.2 tok/s
- Workstation Mac Studio 512 GB Runs great 56.9 tok/s
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.