orukeet-gabor-half.q8_0 needs about 1.3 GB of memory at Q8_0 (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.7 GB to 1.3 GB (F16).
25‑language speech recognizer built on NVIDIA Parakeet TDT 0.6B v3
Orukeet is a 25‑language ASR model derived from Parakeet TDT 0.6B v3. It replaces half of the encoder’s temporal depthwise filters with 12,288 frozen Gabor kernels and trains the remaining parameters on multilingual and multi‑accent data. The model is released under a CC‑BY‑SA‑4.0 license.
Good at
- Multilingual speech‑to‑text in 25 European languages
- Automatic punctuation and capitalization
- Accurate word‑level timestamps
Limits
- No vision support
- Requires 8‑k context for memory estimates
- License is CC‑BY‑SA‑4.0
Best for
- Batch transcription of multilingual audio
- Server‑side speech‑to‑text workers
- Interactive voice‑assistant back‑end
Who it’s for. Developers building multilingual speech‑to‑text services or products that need accurate transcription across European languages. The model is suitable for both commercial and non‑commercial use under the CC‑BY‑SA‑4.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.7 GB | 1.3 GB | Fits | Get file → | |
| Q8_0 | 0.7 GB | 1.3 GB | Fits | Get file → | |
| Q8_0 | 0.7 GB | 1.3 GB | Fits | Get file → | |
| F16 | 1.3 GB | 2.0 GB | Fits | Get file → |
For 8‑GB VRAM, use the Q8_0 quantized file (0.74 GB, ~1.3 GB memory at 8k context). For 16‑GB VRAM, the F16 quantized file (1.3 GB, ~2 GB memory) provides higher precision. The unknown quant file is 0.71 GB but memory estimate is not provided.
What GPU do you need for orukeet-gabor-half.q8_0?
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 F16 (1.3 GB file, about 2.0 GB in use).
Which orukeet-gabor-half.q8_0 quant should you choose?
Q8_0 (0.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is the first one in the table at 0.7 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about orukeet-gabor-half.q8_0
How much VRAM does orukeet-gabor-half.q8_0 need?
About 1.3 GB at Q8_0 with an 8K context window. That is the 0.7 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 orukeet-gabor-half.q8_0 on an 8 GB GPU?
Yes, with F16: the 1.3 GB file needs about 2.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of orukeet-gabor-half.q8_0 GGUF?
It depends on the quant: file is 0.7 GB, Q8_0 is 0.7 GB, Q8_0 is 0.7 GB, F16 is 1.3 GB.
Where can I download orukeet-gabor-half.q8_0 GGUF?
The files are on Hugging Face in the oruk/orukeet repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does orukeet-gabor-half.q8_0 use?
Hugging Face lists the license as cc-by-sa-4.0. 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 Orukeet on 8 GB VRAM?
Yes, the Q8_0 quantized file is 0.74 GB and requires about 1.3 GB memory at 8k context, which fits in 8 GB VRAM.
Does Orukeet support vision tasks?
No, Orukeet is an ASR model and does not support vision.
What license does Orukeet use?
Orukeet is released under the CC‑BY‑SA‑4.0 license.