WH

Whisper Medium (English)

WhisperGGUF by handy-computerUpdated 2026-10-16
Download on Hugging Face
Parameters764M
Context—
Layers—
Architecturewhisper
Smallest quant0.5 GB
Quick answer

Whisper Medium (English) needs about 1.1 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.5 GB (Q4_K_M) to 3.1 GB (F32).

Whisper Medium (English) – 0.764 B parameters for English speech recognition

Whisper Medium (English) is a 0.764 B parameter encoder‑decoder transformer trained on 680k hours of labelled English speech. It is optimized for short‑form transcription of up to 30‑second audio windows and supports chunked long‑form decoding. The model is released under Apache‑2.0.

Good at

  • English speech recognition
  • Short‑form transcription
  • Chunked long‑form decoding

Limits

  • No multilingual or translation support
  • Requires 16 kHz mono WAV input
  • No vision capabilities

Best for

  • Transcribing podcasts
  • Generating subtitles for videos
  • Batch processing of short audio clips

Who it’s for. Developers building offline transcription tools or integrating speech recognition into applications that need a lightweight, English‑only model. The model is suitable for users who prefer open‑source licensing and do not require multilingual or vision features.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.5 GB 1.1 GB
Fits Get file →
Q5_K_M0.6 GB 1.2 GB
Fits Get file →
Q6_K0.6 GB 1.2 GB
Fits Get file →
Q8_00.8 GB 1.4 GB
Fits Get file →
F161.5 GB 2.2 GB
Fits Get file →
F323.1 GB 3.9 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.5 GB, ~1.1 GB memory at 8k context) or Q5_K_M (0.58 GB, ~1.2 GB). For 12 GB VRAM, Q6_K (0.65 GB, ~1.2 GB) or Q8_0 (0.83 GB, ~1.4 GB) are suitable. Higher precision F16 or F32 requires 2.2–3.9 GB memory and larger VRAM.

What GPU do you need for Whisper Medium (English)?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is F32 (3.1 GB file, about 3.9 GB in use).

Which Whisper Medium (English) quant should you choose?

Q4_K_M is the usual starting point for Whisper Medium (English): it balances file size and quality well. Here it is a 0.5 GB file.

The Q8_0 file is 0.8 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturewhisper
Parameters764M

Source

Quantized byhandy-computer
FamilyWhisper
Licenseapache-2.0
Downloads (HF)14,004
Last updated2026-10-16

Frequently asked questions about Whisper Medium (English)

How much VRAM does Whisper Medium (English) need?

About 1.1 GB at Q4_K_M with an 8K context window. That is the 0.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Whisper Medium (English) on an 8 GB GPU?

Yes, with F32: the 3.1 GB file needs about 3.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Whisper Medium (English) GGUF?

It depends on the quant: Q4_K_M is 0.5 GB, Q5_K_M is 0.6 GB, Q6_K is 0.6 GB, Q8_0 is 0.8 GB, F16 is 1.5 GB, F32 is 3.1 GB.

Where can I download Whisper Medium (English) GGUF?

The files are on Hugging Face in the handy-computer/whisper-medium.en-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Whisper Medium (English) use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Whisper Medium on 8 GB VRAM?

Yes, using Q4_K_M or Q5_K_M quantizations keeps VRAM usage below 8 GB.

Does this model support multilingual transcription?

No, Whisper Medium (English) is English‑only; multilingual transcription requires a multilingual checkpoint.

What audio format does it need?

Input must be a 16 kHz mono WAV file; other formats should be converted before inference.

Other GGUFs of whisper-medium.en

Similar models

Browse all →

More from handy-computer

All by handy-computer →

More Whisper models

All Whisper →

Other tiny models

All tiny models →