sarashina2.2-3b-instruct-v0.1-4bit
mlx-community/sarashina2.2-3b-instruct-v0.1-4bit
Text generation · mlx
4-bit Open on Hugging Face
Parameters
3.4B
Weights (est.)
≈ 1.9 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/sarashina2.2-3b-instruct-v0.1-4bit --prompt "Hello"
Details
- Base model
- sbintuitions/sarashina2.2-3b-instruct-v0.1 (quantized)
- Vendor
- sbintuitions
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 93 in the last 30 days · 615 all time · 1 likes
- Published
- 2025-03-05 · updated 2025-03-05 (1y ago)
- Languages
- ja
- Tags
- llama
Other MLX builds of sbintuitions/sarashina2.2-3b-instruct-v0.1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| sarashina2.2-3b-instruct-v0.1-4bit (this one) | 4-bit | ≈ 1.9 GB | 8 GB+ | 93 |
| sarashina2.2-3b-instruct-v0.1-8bit | 8-bit | ≈ 3.6 GB | 8 GB+ | 88 |
| sarashina2.2-3b-instruct-v0.1 | — | ≈ 6.7 GB | 16 GB+ | 32 |