2-bit Open on Hugging Face
Parameters
572B
Weights (est.)
≈ 179 GB
Mac memory (est.)
256 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/Ling-3.1-flash-1019-oQ2e-mtp --prompt "Hello"
Details
- Base model
- inclusionAI/Ling-3.1-flash-1019 (quantized)
- Vendor
- inclusionAI
- Task
- Text generation
- Quantisation
- 2-bit
- Licence
- mit
- Downloads
- 540 in the last 30 days · 540 all time · 0 likes
- Published
- 2026-10-27 · updated 2026-10-28 (14d ago)
- Tags
- bailing_hybrid, quantized, custom_code
Other MLX builds of inclusionAI/Ling-3.1-flash-1019
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Ling-3.1-flash-1019-oQ2e-mtp (this one) | 2-bit | ≈ 179 GB | 256 GB+ | 540 |
| Ling-3.1-flash-1019-oQ2.5e-mtp | 2-bit | ≈ 179 GB | 256 GB+ | 491 |
| Ling-3.1-flash-1019-oQ3e-mtp | 3-bit | ≈ 250 GB | 512 GB+ | 475 |
| Ling-3.1-flash-1019-oQ4e-mtp | 4-bit | ≈ 322 GB | 512 GB+ | 601 |