Translategemma 27b It needs about 21.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 7 quants, from 14.5 GB (Q3_K_L) to 28.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.
27‑billion‑parameter translation model with vision support
TranslateGemma 27b It is a 27‑billion‑parameter Gemma3 model designed for translation across 55 languages. It accepts text and 896×896 images encoded to 256 tokens, with a 2K token context limit. The model is lightweight enough for deployment on laptops and desktops.
Good at
- High‑quality translation across many languages
- Supports image‑to‑text translation
- Runs on modest hardware
Limits
- Requires 8K context for full performance
- Vision input limited to 896×896 resolution
- License is gemma, not commercial
Best for
- Multilingual translation tasks
- Image caption translation
- Local deployment on limited‑resource devices
Who it’s for. Developers needing a compact translation engine for desktop or cloud environments. The model is suitable for applications that require both text and image translation without heavy GPU requirements.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_L | 14.5 GB | 19.2 GB | Too big | Get file → | |
| Q4_K_S | 15.7 GB | 20.3 GB | Too big | Get file → | |
| Q4_K_M | 16.5 GB | 21.2 GB | Too big | Get file → | |
| Q5_K_S | 18.8 GB | 23.4 GB | Too big | Get file → | |
| Q5_K_M | 19.3 GB | 23.9 GB | Too big | Get file → | |
| Q6_K | 22.2 GB | 26.8 GB | Too big | Get file → | |
| Q8_0 | 28.7 GB | 33.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q3_K_L (14.54 GB, ~19.2 GB memory at 8K context). For 12 GB VRAM, Q4_K_S (15.67 GB, ~20.3 GB memory). For 16 GB VRAM, Q4_K_M (16.55 GB, ~21.2 GB memory). Larger quants provide higher fidelity but need more memory.
What GPU do you need for Translategemma 27b It?
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: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.3 GB file, about 23.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (22.2 GB file, about 26.8 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (28.7 GB file, about 33.4 GB in use).
Which Translategemma 27b It quant should you choose?
Q4_K_M is the usual starting point for Translategemma 27b It: it balances file size and quality well. Here it is a 16.5 GB file.
The Q8_0 file is 28.7 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q3_K_L at 14.5 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 Translategemma 27b It
How much VRAM does Translategemma 27b It need?
About 21.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 Translategemma 27b It on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 19.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Translategemma 27b It GGUF?
It depends on the quant: Q3_K_L is 14.5 GB, Q4_K_S is 15.7 GB, Q4_K_M is 16.5 GB, Q5_K_S is 18.8 GB, Q5_K_M is 19.3 GB, Q6_K is 22.2 GB and 1 more.
What context length does Translategemma 27b It support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.6 GB at 32K.
Where can I download Translategemma 27b It GGUF?
The files are on Hugging Face in the bullerwins/translategemma-27b-it-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 Translategemma 27b It use?
Hugging Face lists the license as gemma. 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 TranslateGemma 27b It on 8 GB VRAM?
Yes, with the Q3_K_L quant the file is 14.54 GB and requires about 19.2 GB of VRAM at 8K context, which is within 8 GB when using CPU or off‑load techniques.
Does this model support image translation?
Yes, it accepts 896×896 images encoded to 256 tokens and can translate text extracted from images.
What is the context length for this model?
The model was trained on 131,072 tokens and supports a 2,000 token input context for inference.