Whisper medium: memory fit on every Jetson module.
Method v1.0 · dataset 2026-09-07 · verified 2026-09-07 · last updated September 2026
0.77 B parameters · 24 layers · 448-token max context. Hugging Face: openai/whisper-medium.
Model facts
| Fact | Value | Note |
|---|---|---|
| Parameters | 0.769 B | |
| Layers | 24 | |
| Hidden size | 1024 | |
| Attention heads | 16 | |
| KV heads | 16 | |
| Head dimension | 64 | |
| Max context | 448 tokens | |
| dtype | float32 | |
| Vocabulary | 51,865 |
OpenAI · hf:openai/whisper-medium · config.json · verified 2026-09-07
“"d_model": 1024, "encoder_layers": 24, "decoder_layers": 24, "encoder_attention_heads": 16, "decoder_attention_heads": 16”
Parameters source
- OpenAI · github:openai/whisper/README.md · verified 2026-09-07 · openai/whisper GitHub README.md · class A
“| medium | 769 M | `medium.en` | `medium` | ~5 GB | ~2x |”
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
Encoder-decoder architecture; fields per-stack (encoder==decoder here). Reference VRAM requirement '~5 GB' from OpenAI README is a generic estimate, not Jetson-measured.
Method and data: Model Memory Fit methodology. Full registry: model-memory.json.
Change the context, concurrency or runtime.
The live engine covers any context length, sequence count, KV precision and runtime, with a permanent link.