handy-computer / automatic-speech-recognition updated 2 months ago

whisper-large-v3-gguf

Ported from upstream commit 06f233f, pinned 2026-04-25. Validated against the transformers reference at transcribe.cpp commit 5.6.1 on 2026-04-26.

Params
Context
Downloads 30d
343 K
Likes
1
Commercial use: allowed apache-2.0 Not gated GGUF 100 languages View on Hugging Face ↗

Download history

daily snapshots · 39 days
▲ 6 K in the last 30 days (1.6%)
349 K311 K
Aug 13Aug 26Sep 8Sep 20

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
whisper-large-v3-Q4_K_M.gguf Q4_K_M 1.0 GB 1.6 GB ✅ Runs comfortably
whisper-large-v3-Q5_K_M.gguf Q5_K_M 1.2 GB 1.8 GB ✅ Runs comfortably
whisper-large-v3-Q6_K.gguf Q6_K 1.3 GB 1.9 GB ✅ Runs comfortably
whisper-large-v3-Q8_0.gguf Q8_0 1.7 GB 2.3 GB ✅ Runs comfortably
whisper-large-v3-F16.gguf GGUF 3.1 GB 3.9 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Licence
apache-2.0
First seen on the Hub
2026-04-27
Base model
whisper-large-v3
Training datasets
undisclosed
Added to our catalog
2026-08-13

Family

Base model and the most-downloaded derivatives in the catalog.

Compare with any automatic-speech-recognition model