8-bit Open on Hugging Face
Parameters
7.6B
Weights (est.)
≈ 8.1 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.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/AceReason-Nemotron-7B-8bit --prompt "Hello"
Details
- Base model
- nvidia/AceReason-Nemotron-7B (quantized)
- Vendor
- NVIDIA
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- nvidia-open-model-license
- Downloads
- 43 in the last 30 days · 238 all time · 0 likes
- Published
- 2025-05-26 · updated 2025-05-26 (1y ago)
- Languages
- en
- Tags
- qwen2, nvidia, reasoning, math, code, reinforcement learning, pytorch
Other MLX builds of nvidia/AceReason-Nemotron-7B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| AceReason-Nemotron-7B-4bit | 4-bit | ≈ 4.3 GB | 8 GB+ | 124 |
| AceReason-Nemotron-7B-8bit (this one) | 8-bit | ≈ 8.1 GB | 16 GB+ | 43 |
| AceReason-Nemotron-7B-bf16 | bf16 | ≈ 15.2 GB | 24 GB+ | 43 |