other
0.756B parameters
Commercial OK
Reviewed May 2026

Distil-Whisper Large v3

756M-param distilled Whisper-large-v3 with the decoder shrunk from 32 to 2 layers. ~6.3x faster than the teacher at near-parity WER on long-form English (1% absolute gap on out-of-distribution sets per the model card).

License: mit·Context: 30 tokens
BLK · VERDICT

Our verdict

OP · Fredoline Eruo|VERIFIED MAY 29, 2026
unrated

Best English ASR/throughput trade-off in the open-source Whisper lineage. Default choice for English-only batch jobs.

Overview

756M-param distilled Whisper-large-v3 with the decoder shrunk from 32 to 2 layers. ~6.3x faster than the teacher at near-parity WER on long-form English (1% absolute gap on out-of-distribution sets per the model card).

Strengths

  • ~6x decoder speedup vs whisper-large-v3 at <1% WER regression
  • Strong long-form transcription via chunked/sequential algorithms
  • First-class transformers + faster-whisper + Whisper.cpp + MLX support
  • MIT license, fully commercial

Weaknesses

  • English-only — non-English audio degrades sharply
  • Decoder is shallow — slightly worse on rare-word recovery than the teacher
  • Still inherits Whisper's silence-hallucination behavior
  • Needs a GPU or Apple Silicon for true realtime; CPU latency lags Parakeet

Quantization variants

Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.

QuantizationFile sizeVRAM required
Q4_K_M0.4 GB1 GB

Get the model

HuggingFace

Original weights

huggingface.co/distil-whisper/distil-large-v3

Source repository — direct quantization required.

Hardware that runs this

Cards with enough VRAM for at least one quantization of Distil-Whisper Large v3.

Compare alternatives

Models worth comparing

Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.

Step down
Smaller — faster, runs on weaker hardware
No verdicted models in the next tier down yet.

Frequently asked

What's the minimum VRAM to run Distil-Whisper Large v3?

1GB of VRAM is enough to run Distil-Whisper Large v3 at the Q4_K_M quantization (file size 0.4 GB). Higher-quality quantizations need more.

Can I use Distil-Whisper Large v3 commercially?

Yes — Distil-Whisper Large v3 ships under the mit, which permits commercial use. Always read the license text before deployment.

What's the context length of Distil-Whisper Large v3?

Distil-Whisper Large v3 supports a context window of 30 tokens (about 0K).

Source: huggingface.co/distil-whisper/distil-large-v3

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.

Related — keep moving

Before you buy

Verify Distil-Whisper Large v3 runs on your specific hardware before committing money.