Weekly archive
New local AI models, Aug 19–25, 2024
6 open models released Aug 19–25, 2024, with how each runs on five reference devices.
-
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
-
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
-
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
-
49Fair quality (C) · 49 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
-
40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
- Phone iPhone 17 Pro Runs well 14.2 tok/s
- Laptop MacBook Pro M5 Pro 64 GB Runs great 36.8 tok/s
- Gaming PC RTX 5090 32 GB Runs great 58.4 tok/s
- Edge board Jetson Orin NX 16 GB Runs well 14.2 tok/s
- Workstation Mac Studio 512 GB Runs great 49.9 tok/s
-
16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
- Phone iPhone 17 Pro Runs great 45.4 tok/s
- Laptop MacBook Pro M5 Pro 64 GB Runs great 51.4 tok/s
- Gaming PC RTX 5090 32 GB Runs great 349 tok/s
- Edge board Jetson Orin NX 16 GB Runs great 43.2 tok/s
- Workstation Mac Studio 512 GB Runs great 137 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.