NemotronLabs-VoiceChat-11B-mlx-8bit
mlx-community/NemotronLabs-VoiceChat-11B-mlx-8bit
Uncategorised · mlx
8-bit Open on Hugging Face
Parameters
4.3B
Weights (est.)
≈ 6.9 GB
Mac memory (est.)
16 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Details
- Base model
- nvidia/NVIDIA-NemotronLabs-VoiceChat-11B (finetune)
- Vendor
- NVIDIA
- Task
- Uncategorised
- Quantisation
- 8-bit
- Licence
- openmdw-1.1
- Downloads
- 77 in the last 30 days · 584 all time · 8 likes
- Published
- 2026-08-05 · updated 2026-08-05 (3mo ago)
- Tags
- apple-silicon, speech, duplex, speech-to-speech, nemotron, mamba, audio-codec
Other MLX builds of nvidia/NVIDIA-NemotronLabs-VoiceChat-11B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| NemotronLabs-VoiceChat-11B-mlx-4bit | 4-bit | ≈ 5.1 GB | 8 GB+ | 52 |
| NemotronLabs-VoiceChat-11B-mlx-8bit (this one) | 8-bit | ≈ 6.9 GB | 16 GB+ | 77 |
| NemotronLabs-VoiceChat-11B-4bit | 4-bit | ≈ 8.6 GB | 16 GB+ | 415 |
| NemotronLabs-VoiceChat-11B-8bit | 8-bit | ≈ 13.3 GB | 24 GB+ | 485 |
| NemotronLabs-VoiceChat-11B-mlx-bf16 | bf16 | ≈ 22.2 GB | 32 GB+ | 43 |
| NemotronLabs-VoiceChat-11B-bf16 | bf16 | ≈ 22.2 GB | 32 GB+ | 36 |