MLX Community · First MLX build 5 Aug 2026
NemotronLabs-VoiceChat-11B
MLX
openmdw-1.1 Trending
A 11B parameter model, with 6 MLX builds, from 4-bit to bf16.
- Parameters
- 11B From Hugging Face
- Quantisation
- 8-bit NemotronLabs-VoiceChat-11B-8bit
- Memory needed
- 17 GB Estimate, unified memory
- Download
- 13.3 GB Weights, estimated
- Downloads
- 497 This build, last 30 days
- Task
- —
- MLX builds
- 6 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 17 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 · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/NemotronLabs-VoiceChat-11B-8bitMLX builds
6 on mlx-community| NemotronLabs-VoiceChat-11B-mlx-4bit | 4-bit | 5.1 GB | 8 GB | 54 |
|---|---|---|---|---|
| NemotronLabs-VoiceChat-11B-mlx-8bit | 8-bit | 6.9 GB | 10 GB | 82 |
| NemotronLabs-VoiceChat-11B-4bit | 4-bit | 8.6 GB | 12 GB | 420 |
| NemotronLabs-VoiceChat-11B-8bit | 8-bit | 13.3 GB | 17 GB | 497 |
| NemotronLabs-VoiceChat-11B-mlx-bf16 | bf16 | 22.2 GB | 27 GB | 43 |
| NemotronLabs-VoiceChat-11B-bf16 | bf16 | 22.2 GB | 27 GB | 39 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.