What GPU do I need to run imvladikon/wav2vec2-xls-r-300m-hebrew?

315M parameters, published in F32. View on Hugging Face

315M
Parameters
F32
Native precision
Wav2Vec2ForCTC
Architecture
automatic-speech-recognition
Pipeline

wav2vec2-xls-r-300m-hebrew is published by imvladikon on Hugging Face, with 1,087,980 downloads and 6 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.

PrecisionWeight sizeRequired VRAMCheapest live fitGPUs neededEst. $/hr (full fit)
FP321.2 GB1.4 GBRTX 30701$0.088/hr
FP8 (quantized)0.3 GB0.4 GBRTX 5060 Ti1$0.180/hr
INT4 (quantized)0.1 GB0.2 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 wav2vec2-xls-r-300m-hebrew 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.

wav2vec2-xls-r-300m-hebrew: common questions

How much VRAM does wav2vec2-xls-r-300m-hebrew need?

1.4 GB at FP32, 0.4 GB at FP8 (quantized), 0.2 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 1.2 GB of weights plus inference overhead is the whole requirement.

Can wav2vec2-xls-r-300m-hebrew run in 16-bit instead of FP32?

Yes. Its published weights are FP32, 1.2 GB, or 1.4 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 0.6 GB, or 0.7 GB with overhead. How much accuracy the cast costs is model-specific and is not measured here.

How many copies of wav2vec2-xls-r-300m-hebrew fit on one RTX 3070?

5, by VRAM alone. That card carries 8.0 GB and one copy needs 1.4 GB at FP32, on a live rate of $0.088/hr for the whole card. Throughput is not modelled here, so 5 copies is not 5 times the requests served.

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

More Wav2Vec 2.0 models

All 32 Wav2Vec 2.0 models: VRAM and GPU requirements

Alternatives at this size

Other models for automatic-speech-recognition within about a third of wav2vec2-xls-r-300m-hebrew's 315M parameters, from other model lines.

More on wav2vec2-xls-r-300m-hebrew

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

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.