Index Translate 35B A3B Preview needs about 15.1 GB of memory at its main file (a 13.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 4 quants, from 12.5 GB to 23.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
35B-total / 3B-active multilingual translation model
Index Translate 35B A3B Preview is a 35.5B parameter mixture-of-experts model built on Qwen3.5. It translates across 150 languages and follows detailed translation instructions. The model supports multimodal image translation without external OCR tools.
Good at
- Multilingual translation across 150 languages
- Instruction following with hard and soft constraints
- Multimodal image-to-text translation
Limits
- Requires large VRAM for full model
- No official vision support beyond image translation
- Apache-2.0 license limits commercial use without attribution
Best for
- Enterprise translation pipelines
- Multilingual content localization
- Image translation for global media
Who it’s for. Developers and data scientists building translation services that need high-quality, constrained translations in many languages. The model is suitable for teams that can allocate sufficient GPU memory and comply with the Apache-2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 12.5 GB | 13.7 GB | Too big | Get file → | |
| — | 13.9 GB | 15.1 GB | Too big | Get file → | |
| — | 17.1 GB | 18.3 GB | Too big | Get file → | |
| — | 23.5 GB | 24.7 GB | Too big | Get file → |
For 8 GB VRAM, use the 12.47 GB quant with estimated 13.7 GB memory at 8 k context. For 12 GB VRAM, the 13.87 GB quant uses about 15.1 GB memory. Larger GPUs can run the 17.09 GB or 23.51 GB quantizations, which need 18.3 GB and 24.7 GB respectively. Estimates are approximate.
What GPU do you need for Index Translate 35B A3B Preview?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is the main file (13.9 GB file, about 15.1 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (17.1 GB file, about 18.3 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (23.5 GB file, about 24.7 GB in use).
Which Index Translate 35B A3B Preview quant should you choose?
If memory is tight, the smallest file is the first one in the table at 12.5 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
Frequently asked questions about Index Translate 35B A3B Preview
How much VRAM does Index Translate 35B A3B Preview need?
About 15.1 GB at its main file with an 8K context window. That is the 13.9 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 Index Translate 35B A3B Preview on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Index Translate 35B A3B Preview GGUF?
It depends on the quant: file is 12.5 GB, file is 13.9 GB, file is 17.1 GB, file is 23.5 GB.
What context length does Index Translate 35B A3B Preview support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.8 GB at 32K.
Where can I download Index Translate 35B A3B Preview GGUF?
The files are on Hugging Face in the alphaZimuth/Index-Translate-35B-A3B-preview-APEX-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 Index Translate 35B A3B Preview 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 this model on 8 GB VRAM?
The smallest quantization is 12.47 GB, which requires about 13.7 GB memory at 8 k context, so 8 GB VRAM is insufficient.
Does the model support vision tasks?
It natively supports multimodal image translation but does not provide general vision capabilities beyond that.
What license applies to this model?
The model is released under the Apache-2.0 license, requiring attribution for commercial use.