yandex · First MLX build 24 May 2025
YandexGPT-5-Lite-8B-instruct
MLX
Text yandexgpt-5-lite-8b
A 8B parameter text generation model from yandex, with 2 MLX builds, from 2-bit to 4-bit.
- Parameters
- 8B From Hugging Face
- Quantisation
- 2-bit YandexGPT-5-Lite-8B-instruct-q2
- Memory needed
- 5 GB Estimate, unified memory
- Download
- 2.5 GB Weights, estimated
- Downloads
- 81 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 5 GB at 2-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/YandexGPT-5-Lite-8B-instruct-q2 --prompt "Hello"MLX builds
2 on mlx-community| YandexGPT-5-Lite-8B-instruct-q2 | 2-bit | 2.5 GB | 5 GB | 81 |
|---|---|---|---|---|
| YandexGPT-5-Lite-8B-instruct-4bit | 4-bit | 4.5 GB | 8 GB | 50 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.