4-bit Open on Hugging Face
Parameters
2.2B
Weights (est.)
≈ 1.3 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/Youtu-LLM-2B-4bit --prompt "Hello"
Details
- Base model
- tencent/Youtu-LLM-2B (quantized)
- Vendor
- tencent
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- tencent-youtu
- Downloads
- 62 in the last 30 days · 1.5K all time · 4 likes
- Published
- 2026-01-01 · updated 2026-01-01 (10mo ago)
- Tags
- mlx-lm, deepseek_v2, apple-silicon, tencent, youtu, reasoning, custom_code
Other MLX builds of tencent/Youtu-LLM-2B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Youtu-LLM-2B-mlx-4bit | 4-bit | ≈ 1.1 GB | 8 GB+ | 25 |
| Youtu-LLM-2B-4bit (this one) | 4-bit | ≈ 1.3 GB | 8 GB+ | 62 |
| Youtu-LLM-2B-mlx | — | ≈ 3.9 GB | 8 GB+ | 20 |
| Youtu-LLM-2B | — | ≈ 4.4 GB | 8 GB+ | 47 |