What GPU do I need to run distil-whisper/distil-large-v3?

756M parameters, published in F16. View on Hugging Face

756M
Parameters
F16
Native precision
WhisperForConditionalGeneration
Architecture
automatic-speech-recognition
Pipeline

distil-large-v3 is published by distil-whisper on Hugging Face, with 638,831 downloads and 379 likes to date. It's a WhisperForConditionalGeneration model built for automatic-speech-recognition, published natively in F16.

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.

PrecisionWeight sizeRequired VRAMCheapest live fitGPUs neededEst. $/hr (full fit)
FP161.4 GB1.7 GBRTX 30701$0.088/hr
FP8 (quantized)0.7 GB0.8 GBRTX 40701$0.154/hr
INT4 (quantized)0.4 GB0.4 GBRTX 30701$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 distil-large-v3 at its published (F16) 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.

distil-large-v3: common questions

How much VRAM does distil-large-v3 need?

1.7 GB at FP16, 0.8 GB at FP8 (quantized), 0.4 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 1.4 GB of weights plus inference overhead is the whole requirement.

How many copies of distil-large-v3 fit on one RTX 3070?

4, by VRAM alone. That card carries 8.0 GB and one copy needs 1.7 GB at FP16, on a live rate of $0.088/hr for the whole card. Throughput is not modelled here, so 4 copies is not 4 times the requests served.

Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.

More distil-whisper models

All 2 distil-whisper models: VRAM and GPU requirements

Alternatives at this size

Other models for automatic-speech-recognition within about a third of distil-large-v3's 756M parameters, from other model lines.

More on distil-large-v3

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

Connect your accounts

One console for the GPU clouds you already use.

Connect your accounts for $20 a month, flat. Your provider bills the GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.