Weekly archive

New local AI models, Jul 22–28, 2024

3 open models released Jul 22–28, 2024, with how each runs on five reference devices.

Mistral Large 2 (123B)

Mistral AI · LLM · 123B · released Jul 24

54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.

Runs on
Memory, every quant and how to run it Check your own device
Llama Guard 3 8B

Meta · Decision · 8.0B · released Jul 22

67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.

Runs on
Memory, every quant and how to run it Check your own device
Hermes 3 (Llama 3.1 8B)

Nous Research · LLM · 8.0B · released Jul 28

48Fair quality (C) · 48 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.

Runs on
- Phone iPhone 17 Pro Runs welltight fit 12.1 tok/s
- Laptop MacBook Pro M5 Pro 64 GB Runs great 40.4 tok/s
- Gaming PC RTX 5090 32 GB Runs great 64.3 tok/s
- Edge board Jetson Orin NX 16 GB Runs well 15.7 tok/s
- Workstation Mac Studio 512 GB Runs great 54.9 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.

Mistral Large 2 (123B)

Llama Guard 3 8B

Hermes 3 (Llama 3.1 8B)