bf16 Open on Hugging Face
Parameters
8.2B
Weights (est.)
≈ 16.4 GB
Mac memory (est.)
24 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.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Orchestrator-8B-bf16 --prompt "Hello"
Details
- Base model
- nvidia/Nemotron-Orchestrator-8B (finetune)
- Vendor
- NVIDIA
- Task
- Text generation
- Quantisation
- bf16
- Licence
- —
- Downloads
- 24 in the last 30 days · 241 all time · 1 likes
- Published
- 2025-11-29 · updated 2025-11-29 (11mo ago)
- Tags
- qwen3
Other MLX builds of nvidia/Nemotron-Orchestrator-8B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Orchestrator-8B-4bit | 4-bit | ≈ 4.6 GB | 8 GB+ | 48 |
| Orchestrator-8B-5bit | 5-bit | ≈ 5.6 GB | 16 GB+ | 29 |
| Orchestrator-8B-6bit | 6-bit | ≈ 6.7 GB | 16 GB+ | 33 |
| Orchestrator-8B-8bit | 8-bit | ≈ 8.7 GB | 16 GB+ | 43 |
| Orchestrator-8B-bf16 (this one) | bf16 | ≈ 16.4 GB | 24 GB+ | 24 |