What GPU do I need to run Chillarmo/whisper-large-v3-turbo-armenian?

809M parameters, published in F32. View on Hugging Face

809M
Parameters
F32
Native precision
WhisperForConditionalGeneration
Architecture
automatic-speech-recognition
Pipeline

whisper-large-v3-turbo-armenian is published by Chillarmo on Hugging Face, with 87,183 downloads and 3 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.

PrecisionWeight sizeRequired VRAMCheapest live fitGPUs neededEst. $/hr (full fit)
FP323.0 GB3.6 GBQuadro M40001$0.046/hr
FP8 (quantized)0.8 GB0.9 GBRTX 5060 Ti1$0.180/hr
INT4 (quantized)0.4 GB0.5 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 whisper-large-v3-turbo-armenian at its published (F32) precision: 1× Quadro M4000, at $0.046/hr per GPU ($0.046/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.

whisper-large-v3-turbo-armenian: common questions

How much VRAM does whisper-large-v3-turbo-armenian need?

3.6 GB at FP32, 0.9 GB at FP8 (quantized), 0.5 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 3.0 GB of weights plus inference overhead is the whole requirement.

Can whisper-large-v3-turbo-armenian run in 16-bit instead of FP32?

Yes. Its published weights are FP32, 3.0 GB, or 3.6 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 1.5 GB, or 1.8 GB with overhead. How much accuracy the cast costs is model-specific and is not measured here.

How many copies of whisper-large-v3-turbo-armenian fit on one Quadro M4000?

2, by VRAM alone. That card carries 8.0 GB and one copy needs 3.6 GB at FP32, on a live rate of $0.046/hr for the whole card. Throughput is not modelled here, so 2 copies is not 2 times the requests served.

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

More Whisper models

All 30 Whisper models: VRAM and GPU requirements

Lineage

Based on whisper-large-v3-turbo.

Alternatives at this size

Other models for automatic-speech-recognition within about a third of whisper-large-v3-turbo-armenian's 809M parameters, from other model lines.

More on whisper-large-v3-turbo-armenian

Related reading: H100 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.