Jinx-org · First MLX build 17 Sept 2025
Jinx-gpt-oss-20b-mxfp4
MLX
Text apache-2.0
A 21B parameter text generation model from Jinx-org, with one MLX build at MXFP4.
- Parameters
- 21B From Hugging Face
- Quantisation
- MXFP4 Jinx-gpt-oss-20b-mxfp4-mlx
- Memory needed
- 19 GB Estimate, unified memory
- Download
- 14.4 GB Weights, estimated
- Downloads
- 173 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 19 GB at MXFP4
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/Jinx-gpt-oss-20b-mxfp4-mlx --prompt "Hello"MLX builds
1 on mlx-community| Jinx-gpt-oss-20b-mxfp4-mlx | MXFP4 | 14.4 GB | 19 GB | 173 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.