jackrabbit-110m-ro.f32 needs about 0.7 GB of memory at Q8_0 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.1 GB (Q8_0) to 0.3 GB (F16).
Jackrabbit 110M Romanian ASR, 116M parameters, FastConformer
Jackrabbit 110M is a Romanian speech recognition model built on FastConformer with TDT and CTC decoders. It transcribes 16 kHz mono audio with punctuation and capitalization. The model is licensed CC‑BY‑NC‑4.0.
Good at
- Fast transcription of Romanian speech
- Punctuated and cased output
- Runs comfortably on CPU
Limits
- No vision support
- License restricts commercial use
- No other languages supported
Best for
- Transcribing Romanian podcasts
- Generating subtitles for Romanian videos
- Batch processing of Romanian audio files
Who it’s for. Developers needing an offline Romanian ASR solution. Researchers working on Romanian speech datasets. Content creators producing Romanian subtitles.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| F16 | 0.3 GB | 0.8 GB | Fits | Get file → |
For 8 GB VRAM, use the Q8_0 quantized file (0.15 GB, ~0.7 GB memory at 8k context). For 4 GB VRAM, use the F16 quantized file (0.26 GB, ~0.8 GB memory at 8k context). Both estimates are approximate.
What GPU do you need for jackrabbit-110m-ro.f32?
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 (0.3 GB file, about 0.8 GB in use).
Which jackrabbit-110m-ro.f32 quant should you choose?
Q8_0 (0.1 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about jackrabbit-110m-ro.f32
How much VRAM does jackrabbit-110m-ro.f32 need?
About 0.7 GB at Q8_0 with an 8K context window. That is the 0.1 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 jackrabbit-110m-ro.f32 on an 8 GB GPU?
Yes, with F16: the 0.3 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of jackrabbit-110m-ro.f32 GGUF?
It depends on the quant: Q8_0 is 0.1 GB, F16 is 0.3 GB.
Where can I download jackrabbit-110m-ro.f32 GGUF?
The files are on Hugging Face in the surogate/jackrabbit-110m-ro repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does jackrabbit-110m-ro.f32 use?
Hugging Face lists the license as cc-by-nc-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 Jackrabbit 110M on 8 GB VRAM?
Yes, the Q8_0 quantized model is 0.15 GB and requires about 0.7 GB memory at 8k context, fitting comfortably on 8 GB VRAM.
Does this model support languages other than Romanian?
No, the model is trained exclusively on Romanian data and only supports Romanian.
Is the model suitable for real‑time streaming?
The base model is offline; for live audio use the Jackrabbit 110M Streaming sibling.