RekaAI · First MLX build 12 Jul 2025
reka-flash-3.1
MLX
apache-2.0
A 21B parameter model from RekaAI, with one MLX build at 6-bit.
- Parameters
- 21B From Hugging Face
- Quantisation
- 6-bit reka-flash-3.1-6bit
- Memory needed
- 21 GB Estimate, unified memory
- Download
- 17.0 GB Weights, estimated
- Downloads
- 23 This build, last 30 days
- Task
- —
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 21 GB at 6-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 · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/reka-flash-3.1-6bitMLX builds
1 on mlx-community| reka-flash-3.1-6bit | 6-bit | 17.0 GB | 21 GB | 23 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.