source languages: nl; target languages: en; OPUS readme: nl-en; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.
Open-weight model · Translation
Index-Echo-S2ST-9B-GGUF
by Index Team IndexTeam/Index-Echo-S2ST-9B-GGUF
Index-Echo-S2ST-9B-GGUF is an open-weight model for translation from Index Team, released under Apache License 2.0. Its published files total 81.4 GB.
Official GGUF conversion of the text LLM backbone (stlmllm/) of IndexTeam/Index-Echo-S2ST-9B, part of the Index-Echo speech-to-speech translation (S2ST) model family by bilibili.
Parameters—
Context—
Weights81.4 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—
Model Card
By Index Team, published under apache-2.0, revision eab26eee4405.
Official GGUF conversion of the text LLM backbone (stlmllm/) of IndexTeam/Index-Echo-S2ST-9B, part of the Index-Echo speech-to-speech translation (S2ST) model family by bilibili. Converted with llama.cpp (master, 2026-10); static post-training quantization, all bit-widths in this single repository. (sorted by size) Before release, each quantization tier was validated on GPU (NVIDIA A100) against the F16 conversion: per-token KL divergence / RMS delta-p via llama-perplexity, plus greedy-generation spot checks against the original BF16 weights (transformers reference). Generation outputs of Q4KM matched the reference almost verbatim. Converted and published by the Index team, 2026-10-03.
Read Index Team's full model card
Official GGUF conversion of the text LLM backbone (stlm_llm/) of IndexTeam/Index-Echo-S2ST-9B, part of the Index-Echo speech-to-speech translation (S2ST) model family by bilibili.
Note: LLM backbone only. The audio tower, connector and speech-synthesis stack are not included - llama.cpp cannot run the full speech pipeline. For full speech-to-speech translation (S2ST) inference, use the original checkpoint or the FP8 build in Index-Echo-S2ST-9B-FP8, which ships the complete pipeline with an FP8-quantized LLM.
Converted with llama.cpp (master, 2026-10); static post-training quantization, all bit-widths in this single repository.
Provided files
(sorted by size)
| File | Size | Notes |
|---|---|---|
| Q2_K | 3.83 GB | 2-bit, significant quality loss |
| Q3_K_S | 4.26 GB | 3-bit, noticeable quality loss |
| Q3_K_M | 4.62 GB | 3-bit, noticeable quality loss |
| Q3_K_L | 4.93 GB | 3-bit, noticeable quality loss |
| IQ4_XS | 5.23 GB | 4-bit I-quant, small |
| Q4_K_S | 5.35 GB | 4-bit, slightly smaller/faster |
| Q4_K_M | 5.63 GB | 4-bit, good balance, recommended |
| Q5_K_S | 6.31 GB | 5-bit, low quality loss |
| Q5_K_M | 6.47 GB | 5-bit, low quality loss |
| Q6_K | 7.36 GB | 6-bit, very low quality loss |
| Q8_0 | 9.53 GB | 8-bit, near-lossless |
| f16 | 17.92 GB | 16-bit, lossless conversion baseline |
Usage
# Run the recommended Q4_K_M directly:
llama serve -hf IndexTeam/Index-Echo-S2ST-9B-GGUF:Q4_K_M
llama cli -hf IndexTeam/Index-Echo-S2ST-9B-GGUF:Q4_K_M
Consistency validation
Before release, each quantization tier was validated on GPU (NVIDIA A100) against the F16 conversion: per-token KL divergence / RMS delta-p via llama-perplexity, plus greedy-generation spot checks against the original BF16 weights (transformers reference). Generation outputs of Q4_K_M matched the reference almost verbatim.
Converted and published by the Index team, 2026-10-03.
Identity and Version
- Repository
- IndexTeam/Index-Echo-S2ST-9B-GGUF
- Publisher
- Index Team
- Task
- Translation
- Modality
- Text
- Library
- llama.cpp
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- eab26eee440555d4b6838af2609d12758f33c357
- First published
- 2026-10-02
- Last updated
- 2026-10-03
Files and Weights
15 files, 81.4 GB in total. The weights are 12 files totalling 81.4 GB in gguf.
Weights12 files · 81.4 GB
Documentation1 file · 3.5 KB
Other1 file · 1.2 KB
Repository1 file · 2.3 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| Index-Echo-S2ST-9B.IQ4_XS.gguf | Weights | 5.2 GB | 46bece170cad |
| Index-Echo-S2ST-9B.Q2_K.gguf | Weights | 3.8 GB | 7039f8ee9331 |
| Index-Echo-S2ST-9B.Q3_K_L.gguf | Weights | 4.9 GB | 8dac84ab9748 |
| Index-Echo-S2ST-9B.Q3_K_M.gguf | Weights | 4.6 GB | 70f1832a5c92 |
| Index-Echo-S2ST-9B.Q3_K_S.gguf | Weights | 4.3 GB | 9a527ab00bdb |
| Index-Echo-S2ST-9B.Q4_K_M.gguf | Weights | 5.6 GB | 452a87a2c9e0 |
| Index-Echo-S2ST-9B.Q4_K_S.gguf | Weights | 5.4 GB | bea39e62ec7e |
| Index-Echo-S2ST-9B.Q5_K_M.gguf | Weights | 6.5 GB | 77f7cb8c289d |
| Index-Echo-S2ST-9B.Q5_K_S.gguf | Weights | 6.3 GB | 2cd44eeee1c6 |
| Index-Echo-S2ST-9B.Q6_K.gguf | Weights | 7.4 GB | 48608d9acd0a |
| Index-Echo-S2ST-9B.Q8_0.gguf | Weights | 9.5 GB | fbb47646258d |
| Index-Echo-S2ST-9B.f16.gguf | Weights | 17.9 GB | 74bbf6c405a9 |
| README.md | Documentation | 3.5 KB | — |
| SHA256SUMS.txt | Other | 1.2 KB | — |
| .gitattributes | Repository | 2.3 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 81.4 GB
Download from Index Team
Released by Index Team through its official repository on Hugging Face. Read the license.
Built From
- Derived from IndexTeam/Index-Echo-S2ST-9B
- Quantized from IndexTeam/Index-Echo-S2ST-9B
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 81.4 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Index-Echo-S2ST-9B-GGUF
Can I use Index-Echo-S2ST-9B-GGUF commercially?
Yes. Index-Echo-S2ST-9B-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.