What GPU do I need to run ibm-granite/granite-speech-5.0-470m-turboctc-nc?
473M parameters, published in BF16. View on Hugging Face
Set up granite-spe…470m-turboctc-ncgranite-speech-5.0-470m-turboctc-nc is published by ibm-granite on Hugging Face, with 891 downloads and 30 likes to date. It's a GraniteSpeech5ForCTC model built for automatic-speech-recognition, published natively in BF16.
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.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 0.9 GB | 1.1 GB | RTX 4070 Super | 1 | $0.121/hr |
| FP8 (quantized) | 0.4 GB | 0.5 GB | RTX 4070 Super | 1 | $0.121/hr |
| INT4 (quantized) | 0.2 GB | 0.3 GB | RTX 4070 Super | 1 | $0.121/hr |
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 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run granite-speech-5.0-470m-turboctc-nc at its published (BF16) precision: 1× RTX 4070 Super, at $0.121/hr per GPU ($0.121/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
granite-speech-5.0-470m-turboctc-nc: common questions
How much VRAM does granite-speech-5.0-470m-turboctc-nc need?
1.1 GB at BF16, 0.5 GB at FP8 (quantized), 0.3 GB at INT4 (quantized). All of those sit under 6 GB, the smallest capacity this page reasons about, so VRAM is not what limits where this model runs. The 0.9 GB of weights plus inference overhead is the whole requirement.
How many copies of granite-speech-5.0-470m-turboctc-nc fit on one RTX 4070 Super?
11, by VRAM alone. That card carries 12.0 GB and one copy needs 1.1 GB at BF16, on a live rate of $0.121/hr for the whole card. Throughput is not modelled here, so 11 copies is not 11 times the requests served.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Granite Speech models
- granite-speech-5.0-470m-turboctc (473M, BF16)
- granite-speech-4.1-2b-plus (2.1B, BF16)
- granite-speech-4.1-2b (2.3B, BF16)
- granite-speech-3.3-2b (3.0B, BF16)
- granite-speech-3.2-8b (8.5B, BF16)
Alternatives at this size
Other models for automatic-speech-recognition within about a third of granite-speech-5.0-470m-turboctc-nc's 473M parameters, from other model lines.
- nemotron-3.5-asr-streaming-0.6b (638M, F32)
- parakeet-tdt-0.6b-v3 (627M, F32)
- VibeVoice-ASR-BitNet (323M, F32)
- my_zh_CN_asr_cv13_model (319M, F32)
More on granite-speech-5.0-470m-turboctc-nc
Fits on an 8 GB GPU at BF16: every model that fits in 8 GB.
Best speech-to-text models: how granite-speech-5.0-470m-turboctc-nc ranks against the rest.
Related reading: H100 pricing and specs, Whisper variants compared, and What AI inference is.
