source languages: nl; target languages: en; OPUS readme: nl-en; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.
Open-weight model · Translation
Sugoi-14B-Ultra-GGUF
by Sugoi Toolkit sugoitoolkit/Sugoi-14B-Ultra-GGUF
Unleashing the full potential of the previous sugoi 14B model, Sugoi 14B Ultra delivers near-double translation accuracy compared to its quantized predecessor—achieving a BLEU score of 21.38 vs 13.67.
Parameters—
Context—
Weights60.0 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads24.2k
Model Card
By Sugoi Toolkit, published under apache-2.0, revision d8dd836bf519.
Unleashing the full potential of the previous sugoi 14B model, Sugoi 14B Ultra delivers near-double translation accuracy compared to its quantized predecessor—achieving a BLEU score of 21.38 vs 13.67. Its prompt-following skills rival those of Qwen 2.5 Base, especially when handling the bracket-heavy text commonly found in RPG Maker projects. - Key Improvements Nearly 2× BLEU score boost over previous quantized version (21.38 vs 13.67). Stronger prompt adherence, especially with RPGM-style bracketed text. - Ideal Use Cases Japanese → English translation—especially for game dialogue or RPG text. Interactive environments—works well with chat UIs like LM Studio. Must include a system prompt…
Read Sugoi Toolkit's full model card
Sugoi LLM 14B Ultra (GGUF version)
Unleashing the full potential of the previous sugoi 14B model, Sugoi 14B Ultra delivers near-double translation accuracy compared to its quantized predecessor—achieving a BLEU score of 21.38 vs 13.67. Its prompt-following skills rival those of Qwen 2.5 Base, especially when handling the bracket-heavy text commonly found in RPG Maker projects.
Model Overview
- Key Improvements
- Nearly 2× BLEU score boost over previous quantized version (21.38 vs 13.67).
-
Stronger prompt adherence, especially with RPGM-style bracketed text.
-
Ideal Use Cases
- Japanese → English translation—especially for game dialogue or RPG text.
- Interactive environments—works well with chat UIs like LM Studio.
System Prompt & Settings
Must include a system prompt for best performance:
You are a professional localizer whose primary goal is to translate Japanese to English. You should use colloquial or slang or nsfw vocabulary if it makes the translation more accurate. Always respond in English.
Additional recommendations:
- Context length: ~10 lines (too much may degrade quality).
- In LM Studio, you can interactively ask grammar or context questions, or switch target language via the prompt (quality may vary).
Experimental Features
These features are experimental and may need tuning:
- Tool Integration & JSON Output
- RPGM Tag Preservation
Recommended Sampling Parameters
| Parameter | Value |
|---|---|
| Temperature | 0.1 |
| Top-K | 40 |
| Top-P | 0.95 |
| Min-P | 0.05 |
| Repeat Penalty | 1.1 |
Evaluation & Comparison
- Quantitative: BLEU score doubled vs prior version (21.38 vs 13.67).
- Qualitative: Effective with prompt complexity and RPG Maker markup—delivers clean and accurate translations.
Limitations & Usage Notes
- Overly long context may “poison” the output—keep it around 10 lines for best results.
- Experimental features like JSON formatting and tag preservation may not always work perfectly—review outputs carefully.
- Performance may vary depending on the prompt complexity and UI/tool environment.
- Only uncensored for translation task with translation system prompt, other use case such as roleplay,chat may still trigger qwen censoring.
Getting the Model
Available via Files and Versions tab above. Or search this repo on LM Studio and download the model.
Identity and Version
- Repository
- sugoitoolkit/Sugoi-14B-Ultra-GGUF
- Publisher
- Sugoi Toolkit
- Task
- Translation
- Modality
- Text
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- ja, en
- Revision
- d8dd836bf519a604530779cbf5ce13ffb35c3eeb
- First published
- 2025-08-19
- Last updated
- 2025-08-26
Files and Weights
6 files, 60.0 GB in total. The weights are 4 files totalling 60.0 GB in gguf.
Weights4 files · 60.0 GB
Documentation1 file · 2.7 KB
Repository1 file · 1.8 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| Sugoi-14B-Ultra-F16.gguf | Weights | 29.5 GB | b989796490f6 |
| Sugoi-14B-Ultra-Q2_K.gguf | Weights | 5.8 GB | 66c79943dd39 |
| Sugoi-14B-Ultra-Q4_K_M.gguf | Weights | 9.0 GB | d34cdc5f1be9 |
| Sugoi-14B-Ultra-Q8_0.gguf | Weights | 15.7 GB | d94a055b83b5 |
| README.md | Documentation | 2.7 KB | — |
| .gitattributes | Repository | 1.8 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 60.0 GB
Download from Sugoi Toolkit
Released by Sugoi Toolkit through its official repository on Hugging Face. Read the license.
Built From
- Derived from sugoitoolkit/Sugoi-14B-Ultra-HF
- Quantized from sugoitoolkit/Sugoi-14B-Ultra-HF
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 60.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Sugoi-14B-Ultra-GGUF
Can I use Sugoi-14B-Ultra-GGUF commercially?
Yes. Sugoi-14B-Ultra-GGUF is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models
This is the model card of NLLB-200's distilled 600M variant. Here are the metrics for that particular checkpoint. - Information about training algorithms, parameters, fairness constraints or other applied approaches, and features. The exact training algorithm, data and the strategies to handle data imbalances for high and low resource languages that were used to train NLLB-200 is described in the paper. - Paper or other resource for more information NLLB Team et al, No Language Left Behind: Scaling Human-Centered Machine Translation, Arxiv, 2022 - Where to send questions or comments about the model: https://github.com/facebookresearch/fairseq/issues • Model performance measures: NLLB-200…
source languages: en; target languages: ru; OPUS readme: en-ru; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.
This model can be used for translation and text-to-text generation. CONTENT WARNING: Readers should be aware this section contains content that is disturbing, offensive, and can propagate historical and current stereotypes. Significant research has explored bias and fairness issues with language models (see, e.g., Sheng et al. (2021) and Bender et al. (2021)). Further details about the dataset for this model can be found in the OPUS readme: en-de
hfname: kor-eng - sourcelanguages: kor - targetlanguages: eng - opusreadmeurl: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/kor-eng/README.md - originalrepo: Tatoeba-Challenge - srcconstituents: {'korHani', 'korHang', 'korLatn', 'kor'} - tgtconstituents: {'eng'} - srcmultilingual: False - tgtmultilingual: False - urlmodel: https://object.pouta.csc.fi/Tatoeba-MT-models/kor-eng/opus-2020-06-17.zip - urltestset: https://object.pouta.csc.fi/Tatoeba-MT-models/kor-eng/opus-2020-06-17.test.txt - srcalpha3: kor - tgtalpha3: eng - shortpair: ko-en - chrF2score: 0.588 - brevitypenalty: 0.9590000000000001 - reflen: 17711.0 - srcname: Korean - tgtname: English - traindate…
source languages: de; target languages: en; OPUS readme: de-en; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.