← Back to Models
OpenAItransformer
Whisper Small
0.24B parameters • 0.1GB VRAM (Q4 estimate) • 4,096 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
0.24B
VRAM (Q4 est.)
0.1 GB
VRAM (FP16)
0.48 GB
Context Window
4,096
Architecture
transformer
License
MIT
Finding cloud alternatives...
Run Whisper Small on GTX 1050
~0.1GB 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 Whisper Small
Compatibility Lab — check every GPU × quantization combination