2-bit Open on Hugging Face
Parameters
8.0B
Weights (est.)
≈ 2.5 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/YandexGPT-5-Lite-8B-instruct-q2 --prompt "Hello"
Details
- Base model
- yandex/YandexGPT-5-Lite-8B-instruct (quantized)
- Vendor
- yandex
- Task
- Text generation
- Quantisation
- 2-bit
- Licence
- —
- Downloads
- 81 in the last 30 days · 931 all time · 2 likes
- Published
- 2025-12-15 · updated 2026-03-19 (7mo ago)
- Languages
- ru
- Tags
- llama
Other MLX builds of yandex/YandexGPT-5-Lite-8B-instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| YandexGPT-5-Lite-8B-instruct-q2 (this one) | 2-bit | ≈ 2.5 GB | 8 GB+ | 81 |
| YandexGPT-5-Lite-8B-instruct-4bit | 4-bit | ≈ 4.5 GB | 8 GB+ | 50 |
| YandexGPTQ6 | 6-bit | ≈ 6.5 GB | 16 GB+ | 110 |