Whisper large-v3: memory fit on every Jetson module.

Model facts

OpenAI · hf:openai/whisper-large-v3 · config.json · verified 2026-09-07

“"d_model": 1280, "encoder_layers": 32, "decoder_layers": 32, "encoder_attention_heads": 20, "decoder_attention_heads": 20, "num_mel_bins": 128”

Parameters source

• OpenAI · github:openai/whisper/README.md · verified 2026-09-07 · openai/whisper GitHub README.md · class A

  “| large | 1550 M | N/A | `large` | ~10 GB | 1x |”

Published quantised artefacts

A file the publisher or a community mirror actually ships, used as the class-A weight figure when the requested quant matches. Any quant without a row here falls back to parameters × bytes-per-parameter (class D for block quants).

No published quantised artefact for this model; weights are estimated as parameters × bytes-per-parameter for every quantisation.

Jetson tokens/s measurements

Published or archived throughput numbers, not modelled. Class C (external measured benchmark).

No Jetson-measured tokens/s reported for this model yet.

Every module × every quantisation

Verdict and total memory at 4096-token context, 1 sequence, llama.cpp, headless. Q4 cells link to the static breakdown page; every other cell links to the live engine at that quantisation.

Notes

large-v3 uses 128 mel bins (vs 80 for small/medium/large-v2). Reference VRAM requirement '~10 GB' from OpenAI README is a generic estimate, not Jetson-measured. HF repo also hosts fp16 model.safetensors (1543130976 bytes) confirming ~1.54-1.55B param scale.

Method and data: Model Memory Fit methodology. Full registry: model-memory.json.