parakeet-ultra-gguf
Ported from upstream commit 73175eb, pinned 2026-10-04. Validated against the kestrel 0.9.1 (Photon) reference at transcribe.cpp commit 08f9e6f0 on 2026-10-05.
Params
—
Context
—
Downloads 30d
1,000 K
Likes
6
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)1,000 K downloads in the last 30 days
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-ultra-Q4_K_M.gguf | Q4_K_M | 0.5 GB | 1.0 GB | ✅ Runs comfortably |
| parakeet-ultra-Q5_K_M.gguf | Q5_K_M | 0.5 GB | 1.1 GB | ✅ Runs comfortably |
| parakeet-ultra-Q6_K.gguf | Q6_K | 0.6 GB | 1.2 GB | ✅ Runs comfortably |
| parakeet-ultra-Q8_0.gguf | Q8_0 | 0.7 GB | 1.3 GB | ✅ Runs comfortably |
| parakeet-ultra-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
- Licence
- cc-by-4.0
- First seen on the Hub
- 2026-10-05
- Training datasets
- undisclosed
- Added to our catalog
- 2026-11-06
Compare with any automatic-speech-recognition model