← Back to Models
Hugging Facetransformer
SmolLM 360M
0.36B parameters • 0.2GB VRAM (Q4 estimate) • 2,048 context
Estimate · Q4_K_M · 4k context · batch 1. For dense 7B–70B this sits ~5–8% above the Q4_K_M GGUF file. Not peak runtime VRAM and not a measured bench.
Specifications
Parameters
0.36B
VRAM (Q4 est.)
0.2 GB
VRAM (FP16)
0.72 GB
Context Window
2,048
Architecture
transformer
License
Apache-2.0
Finding cloud alternatives...
Run SmolLM 360M on GTX 1050
~0.2GB VRAM needed at Q4. GTX 1050 has 2GB — buy hardware or rent cloud.
We may earn a commission from cloud and hardware partners at no extra cost to you.
Find the cheapest GPU that can run SmolLM 360M
Compatibility Lab — check every GPU × quantization combination