AceTranslatePro models needs about 2.2 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.9 GB (Q3_K_M) to 1.1 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.
AceTranslatePro models – compact translation and vision toolkit
AceTranslatePro models are 1.78 billion‑parameter dense models built with hunyuan‑dense architecture. They support translation, OCR, layout analysis, speech recognition, and image correction. The models are released under the MIT license.
Good at
- Translation
- OCR
- Image correction
Limits
- No vision support beyond basic image tasks
- Large context requires 262144 tokens
- No mixture of experts
Best for
- Multilingual translation
- Document layout analysis
- Speech‑to‑text
Who it’s for. Developers needing a lightweight, multi‑task model for translation and vision tasks. The models run on standard hardware and are easy to integrate via the provided gguf files.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 0.9 GB | 2.0 GB | Fits | Get file → | |
| — | 0.9 GB | 2.0 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 2.2 GB | Fits | Get file → |
For 8 GB VRAM, use Q3_K_M (0.92 GB, ~2 GB memory). For 12 GB VRAM, Q4_K_M (1.13 GB, ~2.2 GB memory) offers better quality. The unknown quant is similar in size and memory usage.
What GPU do you need for AceTranslatePro models?
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 (1.1 GB file, about 2.2 GB in use).
Which AceTranslatePro models quant should you choose?
Q4_K_M is the usual starting point for AceTranslatePro models: it balances file size and quality well. Here it is a 1.1 GB file.
If memory is tight, the smallest file is Q3_K_M at 0.9 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about AceTranslatePro models
How much VRAM does AceTranslatePro models need?
About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.1 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 AceTranslatePro models on an 8 GB GPU?
Yes, with Q4_K_M: the 1.1 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 AceTranslatePro models GGUF?
It depends on the quant: Q3_K_M is 0.9 GB, file is 0.9 GB, Q4_K_M is 1.1 GB.
What context length does AceTranslatePro models support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.
Where can I download AceTranslatePro models GGUF?
The files are on Hugging Face in the tianclll/AceTranslatePro-models repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does AceTranslatePro models use?
Hugging Face lists the license as mit. 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 AceTranslatePro on 8 GB VRAM?
Yes, the Q3_K_M quant file is 0.92 GB and requires about 2 GB of VRAM at 8k context.
Does the model support vision tasks?
It has basic vision capabilities such as OCR and image correction but no advanced vision features.
What license applies to these models?
The models are released under the MIT license, allowing free use and modification.