MLX Community · First MLX build 25 Jun 2025
Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B
MLX
Text
A 21B parameter text generation model, with one MLX build at 8-bit.
- Parameters
- 21B From Hugging Face
- Quantisation
- 8-bit Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-MLX
- Memory needed
- 27 GB Estimate, unified memory
- Download
- 22.2 GB Weights, estimated
- Downloads
- 247 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 27 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/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-MLX --prompt "Hello"MLX builds
1 on mlx-community| Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-MLX | 8-bit | 22.2 GB | 27 GB | 247 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.