Weekly archive
New local AI models, Nov 4–10, 2024
4 open models released Nov 4–10, 2024, with how each runs on five reference devices.
-
63Good quality (B) · 63 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
-
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
-
36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
- Phone iPhone 17 Pro Runs great 31.4 tok/s
- Laptop MacBook Pro M5 Pro 64 GB Runs great 53.5 tok/s
- Gaming PC RTX 5090 32 GB Runs great 167 tok/s
- Edge board Jetson Orin NX 16 GB Runs great 40.7 tok/s
- Workstation Mac Studio 512 GB Runs great 65.7 tok/s
-
8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
- Phone iPhone 17 Pro Runs great 46.4 tok/s
- Laptop MacBook Pro M5 Pro 64 GB Runs great 155 tok/s
- Gaming PC RTX 5090 32 GB Runs great 1,053 tok/s
- Edge board Jetson Orin NX 16 GB Runs great 60.2 tok/s
- Workstation Mac Studio 512 GB Runs great 415 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.