Weekly archive

New local AI models, Jul 3–9, 2023

1 open model released Jul 3–9, 2023, with how each runs on five reference devices.

InternLM 7B

Shanghai AI Lab · LLM · 7.3B · released Jul 6

12Basic quality (D) · 12 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.

Runs on
- Phone iPhone 17 Pro Runs well 21.7 tok/s
- Laptop MacBook Pro M5 Pro 64 GB Runs great 44.3 tok/s
- Gaming PC RTX 5090 32 GB Runs great 70.5 tok/s
- Edge board Jetson Orin NX 16 GB Runs well 28.2 tok/s
- Workstation Mac Studio 512 GB Runs great 60.2 tok/s
Memory, every quant and how to run it Check your own device

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.

InternLM 7B