parakeet-tdt-0.6b-v3-gguf
Ported from upstream commit 6d590f7, pinned 2026-04-16. Validated against the NeMo reference at transcribe.cpp commit bf0d0b7 on 2026-04-18.
Params
600 M
Context
—
Downloads 30d
1.1 M
Likes
11
Download history
daily snapshots · 106 days
▲ 511 K in the last 30 days (82.2%)
1.1 M620 K
Oct 12Oct 22Nov 1Nov 10
1.1 M558 K
Aug 13Sep 12Oct 12Nov 10
1.1 M477 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 |
|---|---|---|---|---|
| parakeet-tdt-0.6b-v3-Q4_K_M.gguf | Q4_K_M | 0.5 GB | 1.1 GB | ✅ Runs comfortably |
| parakeet-tdt-0.6b-v3-Q5_K_M.gguf | Q5_K_M | 0.5 GB | 1.2 GB | ✅ Runs comfortably |
| parakeet-tdt-0.6b-v3-Q6_K.gguf | Q6_K | 0.6 GB | 1.3 GB | ✅ Runs comfortably |
| parakeet-tdt-0.6b-v3-Q8_0.gguf | Q8_0 | 0.7 GB | 1.4 GB | ✅ Runs comfortably |
| parakeet-tdt-0.6b-v3-F32.gguf | GGUF | 2.5 GB | 3.3 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
- 600 M
- Licence
- cc-by-4.0
- First seen on the Hub
- 2026-04-15
- Base model
- parakeet-tdt-0.6b-v3
- 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