Fimbulvetr-11B-v2-8bit
mlx-community/Fimbulvetr-11B-v2-8bit
Uncategorised · mlx
8-bit Open on Hugging Face
Parameters
11B
Weights (est.)
≈ 11.4 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
- Sao10K/Fimbulvetr-11B-v2 (quantized)
- Vendor
- Sao10K
- Task
- Uncategorised
- Quantisation
- 8-bit
- Licence
- cc-by-nc-4.0
- Downloads
- 59 in the last 30 days · 771 all time · 0 likes
- Published
- 2024-10-20 · updated 2024-10-20 (2y ago)
- Languages
- en
- Tags
- llama
Other MLX builds of Sao10K/Fimbulvetr-11B-v2
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Fimbulvetr-11B-v2-8bit (this one) | 8-bit | ≈ 11.4 GB | 16 GB+ | 59 |
| Fimbulvetr-11B-v2 | — | ≈ 21.5 GB | 32 GB+ | 35 |