wmt21 dense 24 wide en x needs about 6.1 GB of memory at Q8_0 (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 2.7 GB (Q4_K) to 9.4 GB (F16).
4.7B multilingual encoder‑decoder for English‑to‑7‑language translation
The wmt21 dense 24 wide en x model is a 4.7B‑parameter dense encoder‑decoder transformer. It translates English text into Hausa, Icelandic, Japanese, Czech, Russian, Chinese, and German. The model is distributed under the MIT license.
Good at
- High‑quality English‑to‑target language translation
- Supports seven target languages
- Uses forced_bos_token_id for language selection
Limits
- No vision support
- Requires sentencepiece tokenizer
- No domain‑specific fine‑tuning
Best for
- Machine translation pipelines
- Multilingual content localization
- Language‑specific translation services
Who it’s for. Developers building translation services that need a single model for multiple target languages. Researchers needing a dense encoder‑decoder baseline for multilingual translation tasks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 2.7 GB | 3.5 GB | Fits | Get file → | |
| Q8_0 | 5.0 GB | 6.1 GB | Fits | Get file → | |
| F16 | 9.4 GB | 11.0 GB | Too big | Get file → |
For 8 GB VRAM, use the Q4_K quantization (file size 2.67 GB, estimated memory 3.5 GB). If more VRAM is available, Q8_0 (5.01 GB, 6.1 GB) offers higher precision. The full F16 quant (9.41 GB, 11 GB) requires at least 12 GB VRAM.
What GPU do you need for wmt21 dense 24 wide en x?
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 Q4_K (2.7 GB file, about 3.5 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K (2.7 GB file, about 3.5 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (5.0 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (9.4 GB file, about 11.0 GB in use).
Which wmt21 dense 24 wide en x quant should you choose?
Q8_0 (5.0 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.
If memory is tight, the smallest file is Q4_K at 2.7 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about wmt21 dense 24 wide en x
How much VRAM does wmt21 dense 24 wide en x need?
About 6.1 GB at Q8_0 with an 8K context window. That is the 5.0 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 wmt21 dense 24 wide en x on an 8 GB GPU?
Yes, with Q8_0: the 5.0 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of wmt21 dense 24 wide en x GGUF?
It depends on the quant: Q4_K is 2.7 GB, Q8_0 is 5.0 GB, F16 is 9.4 GB.
Where can I download wmt21 dense 24 wide en x GGUF?
The files are on Hugging Face in the cstr/wmt21-dense-24-wide-en-x-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 wmt21 dense 24 wide en x 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 this model on 8 GB VRAM?
Yes, the Q4_K quantization uses about 3.5 GB of VRAM at 8 k context.
Does this model support vision tasks?
No, it is an encoder‑decoder language model only.
What license applies to this model?
The model is distributed under the MIT license.