pandafish-dt-7b-8bit
mlx-community/pandafish-dt-7b-8bit
Uncategorised · mlx
8-bit Open on Hugging Face
Parameters
3.7B
Weights (est.)
≈ 4.0 GB
Mac memory (est.)
8 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
- CultriX/MergeCeption-7B-v3 (finetune)
- Vendor
- CultriX
- Task
- Uncategorised
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 16 in the last 30 days · 184 all time · 0 likes
- Published
- 2024-04-04 · updated 2024-04-04 (2y ago)
- Tags
- mistral, merge, mergekit, lazymergekit, CultriX/MergeCeption-7B-v3
Other MLX builds of CultriX/MergeCeption-7B-v3
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| pandafish-dt-7b-8bit (this one) | 8-bit | ≈ 4.0 GB | 8 GB+ | 16 |
| pandafish-dt-7b | — | ≈ 28.7 GB | 48 GB+ | 10 |