ONIVO speech correction v2 needs about 1.4 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.5 GB (Q4_K_M) to 1.3 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
ONIVO speech correction v2 – text‑only correction model based on Qwen3.5
ONIVO speech correction v2 is a text‑only correction model derived from Qwen3.5. It is fine‑tuned with LoRA and merged into the base weights. The model does not transcribe audio; it corrects transcribed text.
Good at
- Text correction
- Fine‑tuned on speech transcripts
- JSON‑formatted output
Limits
- No vision support
- Small training corpus
- Requires JSON dictation format
Best for
- Post‑processing ASR output
- Editing dictation scripts
- Automated transcription correction
Who it’s for. Developers needing a lightweight correction model for speech transcripts. The model is suitable for research, prototyping, and task‑specific fine‑tuning.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q4_K_M | 1.3 GB | 2.2 GB | Fits | Get file → |
For 8 GB VRAM, use the 0.53 GB Q4_K_M file (≈1.4 GB memory). For 4 GB VRAM, the 1.27 GB Q4_K_M file (≈2.2 GB memory) is too large; a smaller quant would be required. Memory estimates are approximate.
What GPU do you need for ONIVO speech correction v2?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 Q4_K_M (1.3 GB file, about 2.2 GB in use).
Which ONIVO speech correction v2 quant should you choose?
Q4_K_M is the usual starting point for ONIVO speech correction v2: it balances file size and quality well. Here it is a 0.5 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about ONIVO speech correction v2
How much VRAM does ONIVO speech correction v2 need?
About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.5 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 ONIVO speech correction v2 on an 8 GB GPU?
Yes, with Q4_K_M: the 1.3 GB file needs about 2.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of ONIVO speech correction v2 GGUF?
It depends on the quant: Q4_K_M is 0.5 GB, Q4_K_M is 1.3 GB.
What context length does ONIVO speech correction v2 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download ONIVO speech correction v2 GGUF?
The files are on Hugging Face in the minomonchan/ONIVO-speech-correction-v2-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does ONIVO speech correction v2 use?
Hugging Face lists the license as apache-2.0. 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 ONIVO on 8 GB VRAM?
Yes, the 0.53 GB Q4_K_M file requires about 1.4 GB memory at 8 k context.
Does this model support vision input?
No, it is a text‑only correction model and does not transcribe audio.
What license applies to this model?
The model is licensed under apache-2.0.