MLX Community · First MLX build 29 Aug 2026
Qwen3.5-122B-A10B-OptiQ-2bit
MLX
Text apache-2.0
A 65B parameter text generation model, with one MLX build at 2-bit.
- Parameters
- 65B From Hugging Face
- Quantisation
- 2-bit Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B
- Memory needed
- 26 GB Estimate, unified memory
- Download
- 20.9 GB Weights, estimated
- Downloads
- 174 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 26 GB at 2-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/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B --prompt "Hello"MLX builds
1 on mlx-community| Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B | 2-bit | 20.9 GB | 26 GB | 174 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.