What GPU do I need to run facebook/mms-1b-all?
965M parameters, published in F32. View on Hugging Face
mms-1b-all is published by facebook on Hugging Face, with 256,632 downloads and 205 likes to date. It's a Wav2Vec2ForCTC model built for automatic-speech-recognition, published natively in F32.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for activations and allocator fragmentation. Speech models don't build the same growing KV-cache a text model does. Memory scales primarily with input audio length. Full formula and assumptions: methodology.
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 caveat: requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run mms-1b-all at its published (F32) precision: 1× P4 on akash, at $0.032/hr per GPU ($0.032/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More facebook models
- seamless-m4t-v2-large (2.3B, F32)
- wav2vec2-conformer-rope-large-960h-ft (593M, F32)
- wav2vec2-large-robust-ft-libri-960h (315M, F32)
- Qwen3-0.6B (752M, BF16)
- gpt2 (137M, F32)
- Qwen3-8B (8.2B, BF16)
