What GPU do I need to run AbelZimba/whisper-bemba-stt?
242M parameters, published in F32. View on Hugging Face
whisper-bemba-stt is published by AbelZimba on Hugging Face, with 536,447 downloads and 0 likes to date. It's a WhisperForConditionalGeneration 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.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP32 | 0.9 GB | 1.1 GB | RTX 3070 | 1 | $0.088/hr |
| FP8 (quantized) | 0.2 GB | 0.3 GB | RTX 5060 Ti | 1 | $0.180/hr |
| INT4 (quantized) | 0.1 GB | 0.1 GB | RTX 3070 | 1 | $0.088/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 whisper-bemba-stt at its published (F32) precision: 1× RTX 3070, at $0.088/hr per GPU ($0.088/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
whisper-bemba-stt: common questions
How much VRAM does whisper-bemba-stt need?
1.1 GB at FP32, 0.3 GB at FP8 (quantized), 0.1 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.
Can whisper-bemba-stt run in 16-bit instead of FP32?
Yes. Its published weights are FP32, 0.9 GB, or 1.1 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 0.5 GB, or 0.5 GB with overhead. How much accuracy the cast costs is model-specific and is not measured here.
How many copies of whisper-bemba-stt fit on one RTX 3070?
7, by VRAM alone. That card carries 8.0 GB and one copy needs 1.1 GB at FP32, on a live rate of $0.088/hr for the whole card. Throughput is not modelled here, so 7 copies is not 7 times the requests served.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Whisper models
- whisper-small (242M, F32)
- whisper-small.en (242M, F32)
- anime-whisper (756M, F32)
- kotoba-whisper-v2.2 (756M, F32)
- kotoba-whisper-v2.0 (756M, BF16)
Alternatives at this size
Other models for automatic-speech-recognition within about a third of whisper-bemba-stt's 242M parameters, from other model lines.
- BanglaASR (242M, F32)
- VibeVoice-ASR-BitNet (323M, F32)
- distil-small.en (166M, F16)
- mms-300m-1130-forced-aligner (315M, F32)
- romanian-wav2vec2 (315M, F32)
More on whisper-bemba-stt
Fits on an 8 GB GPU at FP32: every model that fits in 8 GB.
Related reading: RTX 3070 pricing and specs, Whisper variants compared, What AI inference is, and What AI model fine-tuning is.
Your own GPU cloud accounts
One console for the GPU clouds you already rent from. Your keys stay on your machine.
$20 a month, flat