MLX Community · First MLX build 26 Apr 2024
Qwen1.5-110B-Chat
MLX
Text tongyi-qianwen
A 111B parameter text generation model, with 2 MLX builds, from 4-bit to 8-bit.
- Parameters
- 111B From Hugging Face
- Quantisation
- 4-bit Qwen1.5-110B-Chat-4bit
- Memory needed
- 72 GB Estimate, unified memory
- Download
- 62.6 GB Weights, estimated
- Downloads
- 57 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 72 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/Qwen1.5-110B-Chat-4bit --prompt "Hello"MLX builds
2 on mlx-community| Qwen1.5-110B-Chat-4bit | 4-bit | 62.6 GB | 72 GB | 57 |
|---|---|---|---|---|
| Qwen1.5-110B-Chat-8bit | 8-bit | 118 GB | 135 GB | 40 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.