Weekly archive
New local AI models, Jan 12–18, 2026
4 open models released Jan 12–18, 2026, with how each runs on five reference devices.
-
79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
-
84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
-
78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
-
3Basic quality (D) · 3 of 100: how capable the model is at F16, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking.
Runs on
- Phone iPhone 17 Pro Runs great 253 tok/s
- Laptop MacBook Pro M5 Pro 64 GB Runs great 846 tok/s
- Gaming PC RTX 5090 32 GB Runs great 5,734 tok/s
- Edge board Jetson Orin NX 16 GB Runs great 328 tok/s
- Workstation Mac Studio 512 GB Runs great 2,257 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.