ChimeraLlama-3-8B-v3-unquantized
mlx-community/ChimeraLlama-3-8B-v3-unquantized
Uncategorised · mlx
Parameters
8.0B
Weights (est.)
≈ 16.1 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.
Details
- Base model
- Danielbrdz/Barcenas-Llama3-8b-ORPO (merge)
- Vendor
- Danielbrdz
- Task
- Uncategorised
- Quantisation
- Not stated
- Licence
- other
- Downloads
- 11 in the last 30 days · 298 all time · 0 likes
- Published
- 2024-05-05 · updated 2024-05-05 (2y ago)
- Tags
- llama, merge, mergekit, lazymergekit