Weekly archive

New local AI models, Jul 29 – Aug 4, 2024

9 open models released Jul 29 – Aug 4, 2024, with how each runs on five reference devices.

FLUX.1 [dev]

Black Forest Labs · Image · 11.9B · released Jul 31

80Great quality (A) · 80 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.

Runs on
Memory, every quant and how to run it Check your own device
FLUX.1 [schnell]

Black Forest Labs · Image · 11.9B · released Jul 31

70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (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 70B)

Nous Research · LLM · 71B · released Jul 29

64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.

Runs on
Memory, every quant and how to run it Check your own device
InternLM2.5 20B Chat

Shanghai AI Lab · LLM · 20B · released Jul 30

47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.

Runs on
- Phone iPhone 17 Pro Won't runover the app memory limit
- Laptop MacBook Pro M5 Pro 64 GB Runs well 16.3 tok/s
- Gaming PC RTX 5090 32 GB Runs great 56.4 tok/s
- Edge board Jetson Orin NX 16 GB Runs well 10.4 tok/s
- Workstation Mac Studio 512 GB Runs great 43.6 tok/s
Memory, every quant and how to run it Check your own device
MiniCPM-V 2.6 8B

OpenBMB · LLM · 8.1B · released Aug 4

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 well 12.0 tok/s
- Laptop MacBook Pro M5 Pro 64 GB Runs great 40.1 tok/s
- Gaming PC RTX 5090 32 GB Runs great 63.7 tok/s
- Edge board Jetson Orin NX 16 GB Runs well 15.5 tok/s
- Workstation Mac Studio 512 GB Runs great 54.4 tok/s
Memory, every quant and how to run it Check your own device
Dolphin 2.9.4 Llama 3.1 8B

Cognitive Computations · LLM · 8.0B · released Aug 4

44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 62/100 (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
EXAONE 3.0 7.8B Instruct

LG AI Research · LLM · 7.8B · released Jul 31

38Basic quality (D) · 38 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.

Runs on
- Phone iPhone 17 Pro Runs well 12.4 tok/s
- Laptop MacBook Pro M5 Pro 64 GB Runs great 41.5 tok/s
- Gaming PC RTX 5090 32 GB Runs great 66.0 tok/s
- Edge board Jetson Orin NX 16 GB Runs well 16.1 tok/s
- Workstation Mac Studio 512 GB Runs great 56.4 tok/s
Memory, every quant and how to run it Check your own device
Falcon Mamba 7B Instruct

TII · LLM · 7.3B · released Jul 30

30Basic quality (D) · 30 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.

Runs on
- Phone iPhone 17 Pro Runs well 13.3 tok/s
- Laptop MacBook Pro M5 Pro 64 GB Runs great 44.6 tok/s
- Gaming PC RTX 5090 32 GB Runs great 71.0 tok/s
- Edge board Jetson Orin NX 16 GB Runs well 17.3 tok/s
- Workstation Mac Studio 512 GB Runs great 60.6 tok/s
Memory, every quant and how to run it Check your own device
InternLM2.5 1.8B Chat

Shanghai AI Lab · LLM · 1.9B · released Jul 30

18Basic quality (D) · 18 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.

Runs on
- Phone iPhone 17 Pro Runs great 42.4 tok/s
- Laptop MacBook Pro M5 Pro 64 GB Runs great 40.3 tok/s
- Gaming PC RTX 5090 32 GB Runs great 273 tok/s
- Edge board Jetson Orin NX 16 GB Runs great 46.1 tok/s
- Workstation Mac Studio 512 GB Runs great 107 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.