ZeroXClem · First MLX build 19 Jan 2026
Qwen3-4B-Sky-High-Hermes
MLX
Text apache-2.0
A 4B parameter text generation model from ZeroXClem, with 4 MLX builds, from 4-bit to 8-bit.
- Parameters
- 4B From Hugging Face
- Quantisation
- 8-bit Qwen3-4B-Sky-High-Hermes-8bit
- Memory needed
- 7 GB Estimate, unified memory
- Download
- 4.3 GB Weights, estimated
- Downloads
- 160 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 7 GB at 8-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/Qwen3-4B-Sky-High-Hermes-8bit --prompt "Hello"MLX builds
4 on mlx-community| Qwen3-4B-Sky-High-Hermes-4bit | 4-bit | 2.3 GB | 5 GB | 33 |
|---|---|---|---|---|
| Qwen3-4B-Sky-High-Hermes-6bit | 6-bit | 3.3 GB | 6 GB | 39 |
| Qwen3-4B-Sky-High-Hermes-8bit | 8-bit | 4.3 GB | 7 GB | 160 |
| Qwen3-4B-Sky-High-Hermes-bfloat16 | Unstated | 8.0 GB | 11 GB | 32 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.