WH

whisper base

WhisperGGUF by oxide-labUpdated 2026-08-17
Download on Hugging Face
Parameters73M
Context—
Layers—
Architecture—
Smallest quant0.0 GB
Quick answer

whisper base needs about 0.6 GB of memory at Q4_1 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 13 quants, from 0.0 GB (Q2_K) to 0.1 GB (Q8_0).

Whisper Base quantized for efficient speech recognition

Whisper Base is a 0.0726B parameter encoder‑decoder model for automatic speech recognition. It is available in multiple GGUF quantizations ranging from Q2_K to Q8_0. The model is licensed under MIT and supports English and multilingual speech tasks.

Good at

  • Speech transcription
  • Speech translation
  • Low‑latency inference

Limits

  • No vision support
  • Limited to 8k context
  • Requires WhisperProcessor

Best for

  • Local ASR on edge devices
  • Batch transcription pipelines
  • Rapid prototyping of speech apps

Who it’s for. Developers needing a lightweight Whisper model for local inference. The quantized GGUF files enable deployment with whisper.cpp or Candle on systems with limited VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.0 GB 0.5 GB
Fits Get file →
Q3_K0.0 GB 0.5 GB
Fits Get file →
Q4_00.0 GB 0.5 GB
Fits Get file →
Q4_00.0 GB 0.6 GB
Fits Get file →
Q4_K0.0 GB 0.6 GB
Fits Get file →
Q4_10.0 GB 0.6 GB
Fits Get file →
Q4_10.1 GB 0.6 GB
Fits Get file →
Q5_00.1 GB 0.6 GB
Fits Get file →
Q5_K0.1 GB 0.6 GB
Fits Get file →
Q5_10.1 GB 0.6 GB
Fits Get file →
Q6_K0.1 GB 0.6 GB
Fits Get file →
Q8_00.1 GB 0.6 GB
Fits Get file →
Q8_00.1 GB 0.6 GB
Fits Get file →

For 8 GB VRAM, Q4_K (0.05 GB) or Q4_1 (0.05 GB) provide a good balance of size and quality. If memory is tighter, Q3_K (0.04 GB) or Q2_K (0.03 GB) are options, though quality may drop. The Q5_0 (0.06 GB) is the recommended high‑quality choice when VRAM allows.

What GPU do you need for whisper base?

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 Q8_0 (0.1 GB file, about 0.6 GB in use).

Which whisper base quant should you choose?

Q4_1 (0.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q2_K at 0.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Parameters73M

Source

Quantized byoxide-lab
FamilyWhisper
Licensemit
Downloads (HF)1,828
Last updated2026-08-17

Frequently asked questions about whisper base

How much VRAM does whisper base need?

About 0.6 GB at Q4_1 with an 8K context window. That is the 0.1 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 base on an 8 GB GPU?

Yes, with Q8_0: the 0.1 GB file needs about 0.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of whisper base GGUF?

It depends on the quant: Q2_K is 0.0 GB, Q3_K is 0.0 GB, Q4_0 is 0.0 GB, Q4_0 is 0.0 GB, Q4_K is 0.0 GB, Q4_1 is 0.0 GB and 7 more.

Where can I download whisper base GGUF?

The files are on Hugging Face in the oxide-lab/whisper-base-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 base use?

Hugging Face lists the license as mit. 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 Base on 8 GB VRAM?

Yes, quantized versions such as Q4_K or Q4_1 fit within 8 GB VRAM and run with whisper.cpp or Candle.

What context length does Whisper Base support?

The model is trained with 8k context tokens; inference is limited to this length.

Is Whisper Base suitable for multilingual speech?

Yes, the base model supports both English-only and multilingual training data for transcription and translation.

Other GGUFs of whisper-base

Similar models

Browse all →

More from oxide-lab

All by oxide-lab →

More Whisper models

All Whisper →

Other tiny models

All tiny models →