8-bit Open on Hugging Face
Parameters
71B
Weights (est.)
≈ 75.0 GB
Mac memory (est.)
96 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/Anubis-70B-v1.1-8bit --prompt "Hello"
Details
- Base model
- TheDrummer/Anubis-70B-v1.1 (quantized)
- Vendor
- TheDrummer
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- —
- Downloads
- 34 in the last 30 days · 302 all time · 0 likes
- Published
- 2025-06-28 · updated 2025-06-28 (1y ago)
- Tags
- llama
Other MLX builds of TheDrummer/Anubis-70B-v1.1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Anubis-70B-v1.1-4bit | 4-bit | ≈ 39.7 GB | 48 GB+ | 33 |
| Anubis-70B-v1.1-6bit | 6-bit | ≈ 57.3 GB | 96 GB+ | 30 |
| Anubis-70B-v1.1-8bit (this one) | 8-bit | ≈ 75.0 GB | 96 GB+ | 34 |
| Anubis-70B-v1.1-bf16 | bf16 | ≈ 141 GB | 192 GB+ | 31 |