bf16 Open on Hugging Face
Parameters
256M
Weights (est.)
≈ 513 MB
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-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/SmolVLM-256M-Instruct-bf16 --image photo.jpg --prompt "Describe this image"
Details
- Base model
- HuggingFaceTB/SmolLM2-135M-Instruct (finetune)
- Vendor
- Hugging Face
- Task
- Vision + text
- Quantisation
- bf16
- Licence
- apache-2.0
- Downloads
- 212 in the last 30 days · 1.3K all time · 1 likes
- Published
- 2025-01-23 · updated 2025-01-23 (1y ago)
- Languages
- en
- Tags
- idefics3
Other MLX builds of HuggingFaceTB/SmolLM2-135M-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| SmolVLM-256M-Instruct-3bit | 3-bit | ≈ 113 MB | 8 GB+ | 47 |
| SmolVLM-256M-Instruct-4bit | 4-bit | ≈ 145 MB | 8 GB+ | 1.3K |
| SmolVLM-256M-Instruct-6bit | 6-bit | ≈ 209 MB | 8 GB+ | 47 |
| SmolLM2-135M-Instruct | — | ≈ 269 MB | 8 GB+ | 4.1K |
| SmolVLM-256M-Instruct-8bit | 8-bit | ≈ 273 MB | 8 GB+ | 101 |
| SmolVLM-256M-Instruct-bf16 (this one) | bf16 | ≈ 513 MB | 8 GB+ | 212 |