JOSIE-TinyLlama-1.1B-32k-base-8bit
mlx-community/JOSIE-TinyLlama-1.1B-32k-base-8bit
Text generation · transformers
8-bit Open on Hugging Face
Parameters
1.1B
Weights (est.)
≈ 1.2 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.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/JOSIE-TinyLlama-1.1B-32k-base-8bit --prompt "Hello"
Details
- Base model
- Doctor-Shotgun/TinyLlama-1.1B-32k (finetune)
- Vendor
- Doctor-Shotgun
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- —
- Downloads
- 34 in the last 30 days · 531 all time · 1 likes
- Published
- 2024-05-24 · updated 2024-05-24 (2y ago)
- Tags
- llama
Other MLX builds of Doctor-Shotgun/TinyLlama-1.1B-32k
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| JOSIE-TinyLlama-1.1B-32k-base-4bit | 4-bit | ≈ 619 MB | 8 GB+ | 49 |
| JOSIE-TinyLlama-1.1B-32k-base-8bit (this one) | 8-bit | ≈ 1.2 GB | 8 GB+ | 34 |