distil-large-v3
distil-whispermitaudio

distil-large-v3

Updated Nov 21, 2026
Parameters
760M
License
mit
Updated
Nov 21, 2026

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at FP16
4 of 4 quantizations fit distil-large-v3 with real runtime overhead.
Q4_K_M
1 GB
Q5_K_M
1 GB
Q8_0
1 GB
FP16
2 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve distil-whisper/distil-large-v3

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

distil-large-v3 is an open-weight speech recognition model published by distil-whisper on Hugging Face in March 2024, with 760M parameters under the mit license.

Among the 25 speech recognition models in this directory it ranks 8th by monthly Hugging Face downloads, and 10 of the others are larger.

HardwareLink to this section

Unquantized FP16 weights take about 2 GB; 8-bit brings that to ~1 GB and 4-bit (Q4_K_M) to ~1 GB, before activations and any context or image buffers. At this size it runs on almost any recent GPU, on Apple Silicon, and usable on a modern CPU. Check exact numbers for your card with the VRAM calculator.

Similar speech recognition modelsLink to this section

PopularityLink to this section

distil-large-v3 was downloaded 745,014 times on Hugging Face in the last month (21,755,912 all-time) and has 386 likes.

Run it locallyLink to this section

Weights and usage instructions are on the distil-whisper/distil-large-v3 model card; it loads with Hugging Face Transformers.

Local runtimes that fit this model:

  • transformers - the reference Python library most model cards target

PaperLink to this section

Frequently asked

Quick answers to common questions

How much VRAM does distil-large-v3 need?

distil-large-v3 with 760M parameters needs approximately 1 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is distil-large-v3 better than other distil-whisper models?

distil-large-v3 has 760M parameters - a strong choice for speech-recognition.

What license is distil-large-v3 under?

distil-large-v3 is released under the mit license, making it suitable for most commercial and personal projects.

What hardware runs distil-large-v3 well?

With 760M parameters, distil-large-v3 is small enough for most consumer GPUs, Apple Silicon Macs, and many CPUs. Check our hardware directory for specific recommendations.

What is the best quantization for distil-large-v3?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~1 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

What models compete with distil-large-v3?

distil-large-v3 competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec