What GPU do I need to run kyutai/stt-2.6b-en-trfs?
2.7B parameters, published in BF16. View on Hugging Face
stt-2.6b-en-trfs is published by kyutai on Hugging Face, with 17,054 downloads and 10 likes to date. It's a KyutaiSpeechToTextForConditionalGeneration 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 | 5.0 GB | 6.0 GB | RTX 3070 | 1 | $0.088/hr |
| FP8 (quantized) | 2.5 GB | 3.0 GB | RTX 5060 Ti | 1 | $0.180/hr |
| INT4 (quantized) | 1.3 GB | 1.5 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 stt-2.6b-en-trfs at its published (BF16) 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.
stt-2.6b-en-trfs: common questions
Does stt-2.6b-en-trfs fit on a 8 GB GPU?
Yes. At BF16 it needs 6.0 GB of VRAM, so an 8 GB card holds it with 2.0 GB to spare. A 6 GB card is not enough for it at BF16.
What is the least VRAM stt-2.6b-en-trfs can run in?
1.5 GB, at INT4 (quantized), which fits a 6 GB card, against 6.0 GB at BF16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More kyutai models
- helium-1-preview-2b (2.2B, BF16)
Alternatives at this size
Other models for automatic-speech-recognition within about a third of stt-2.6b-en-trfs's 2.7B parameters, from other model lines.
- Qwen3-ASR-1.7B (2.3B, BF16)
- cohere-transcribe-03-2026 (2.1B, BF16)
- seamless-m4t-v2-large (2.3B, F32)
- granite-speech-4.1-2b (2.3B, BF16)
- GLM-ASR-Nano-2512 (2.3B, BF16)
More on stt-2.6b-en-trfs
Fits on an 8 GB GPU at BF16: every model that fits in 8 GB.
Best speech-to-text models: how stt-2.6b-en-trfs ranks against the rest.
Related reading: RTX 3070 pricing and specs, Whisper variants compared, and What AI inference 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