Tencent · First MLX build 27 Apr 2026
Hy3-preview
MLX
Text other
A 295B parameter text generation model from Tencent, with 4 MLX builds, from 4-bit to 8-bit.
- Parameters
- 295B From Hugging Face
- Quantisation
- 4-bit Hy3-preview-4bit
- Memory needed
- 188 GB Estimate, unified memory
- Download
- 166 GB Weights, estimated
- Downloads
- 79 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 188 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/Hy3-preview-4bit --prompt "Hello"MLX builds
4 on mlx-community| Hy3-preview-4bit | 4-bit | 166 GB | 188 GB | 79 |
|---|---|---|---|---|
| Hy3-preview-6bit | 6-bit | 240 GB | 270 GB | 33 |
| Hy3-preview-8bit | 8-bit | 313 GB | 353 GB | 26 |
| Hy3-preview-MTP-4bit | 4-bit | — | — | 0 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.