whisper-medium-gguf
Ported from upstream commit abdf7c3, pinned 2026-04-25. Validated against the transformers reference at transcribe.cpp commit 0a26478 on 2026-09-13.
Params
760 M
Context
—
Downloads 30d
662 K
Likes
0
Download history
daily snapshots · 106 days
▲ 72 K in the last 30 days (12.3%)
752 K590 K
Oct 12Oct 22Nov 1Nov 10
752 K489 K
Aug 13Sep 12Oct 12Nov 10
752 K443 K
Jul 28Sep 1Oct 6Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| whisper-medium-Q4_K_M.gguf | Q4_K_M | 0.5 GB | 1.2 GB | ✅ Runs comfortably |
| whisper-medium-Q5_K_M.gguf | Q5_K_M | 0.6 GB | 1.3 GB | ✅ Runs comfortably |
| whisper-medium-Q6_K.gguf | Q6_K | 0.6 GB | 1.3 GB | ✅ Runs comfortably |
| whisper-medium-Q8_0.gguf | Q8_0 | 0.8 GB | 1.5 GB | ✅ Runs comfortably |
| whisper-medium-F32.gguf | GGUF | 3.1 GB | 4.0 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Parameters
- 760 M
- Licence
- apache-2.0
- First seen on the Hub
- 2026-04-27
- Base model
- whisper-medium
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any automatic-speech-recognition model