Weekly archive
New local AI models, Feb 19–25, 2024
5 open models released Feb 19–25, 2024, with how each runs on five reference devices.
-
74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
-
54Fair quality (C) · 54 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
-
31Basic quality (D) · 31 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
-
28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
- Phone iPhone 17 Pro Runs well 16.5 tok/s
- Laptop MacBook Pro M5 Pro 64 GB Runs great 42.9 tok/s
- Gaming PC RTX 5090 32 GB Runs great 68.2 tok/s
- Edge board Jetson Orin NX 16 GB Runs well 16.6 tok/s
- Workstation Mac Studio 512 GB Runs great 58.2 tok/s
-
24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
- Phone iPhone 17 Pro Runs well 17.5 tok/s
- Laptop MacBook Pro M5 Pro 64 GB Runs great 45.3 tok/s
- Gaming PC RTX 5090 32 GB Runs great 72.0 tok/s
- Edge board Jetson Orin NX 16 GB Runs well 22.7 tok/s
- Workstation Mac Studio 512 GB Runs great 61.5 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.