IN

Index Echo S2ST 9B

IndexGGUF by IndexTeamUpdated 2026-10-18
Download on Hugging Face
Parameters8.95B
Context256K
Layers33
Architectureqwen35
Smallest quant3.8 GB
Quick answer

Index Echo S2ST 9B needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 12 quants, from 3.8 GB (Q2_K) to 17.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

Index Echo S2ST 9B – 9B‑parameter speech‑to‑speech translator

Index Echo S2ST 9B translates speech from Chinese, Japanese, or English into another language and generates speech conditioned on the source speaker. The model uses a frozen Index‑Echo‑S2TT backbone, a Hidden2CV mapper, and CosyVoice3 for synthesis. The GGUF package contains only the text LLM backbone.

Good at

  • Multilingual speech translation
  • Voice‑conditioned synthesis
  • Twelve language directions

Limits

  • LLM backbone only – no audio pipeline
  • Requires 8k context for estimates
  • License: apache-2.0

Best for

  • Translating short speeches
  • Generating dubbed audio
  • Research on speech‑to‑speech models

Who it’s for. Developers and researchers needing a lightweight, quantized text backbone for speech‑to‑speech translation. The package is suitable for local inference with llama.cpp but does not include the full audio pipeline.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.8 GB 5.4 GB
Fits Get file →
Q3_K_S4.3 GB 5.9 GB
Fits Get file →
Q3_K_M4.6 GB 6.2 GB
Fits Get file →
Q3_K_L4.9 GB 6.5 GB
Fits Get file →
IQ4_XS5.2 GB 6.8 GB
Fits Get file →
Q4_K_S5.4 GB 7.0 GB
Fits Get file →
Q4_K_M5.6 GB 7.2 GB
Tight Get file →
Q5_K_S6.3 GB 7.9 GB
Tight Get file →
Q5_K_M6.5 GB 8.1 GB
Too big Get file →
Q6_K7.4 GB 9.0 GB
Too big Get file →
Q8_09.5 GB 11.1 GB
Too big Get file →
F1617.9 GB 19.5 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (5.63 GB, 7.2 GB memory) or Q5_K_S (6.31 GB, 7.9 GB). For 12 GB VRAM, Q6_K (7.36 GB, 9 GB) or Q8_0 (9.53 GB, 11.1 GB) are suitable. Higher precision models require more memory.

What GPU do you need for Index Echo S2ST 9B?

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: the best quant that fits is Q3_K_S (4.3 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_S (6.3 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (17.9 GB file, about 19.5 GB in use).

Which Index Echo S2ST 9B quant should you choose?

Q4_K_M is the usual starting point for Index Echo S2ST 9B: it balances file size and quality well. Here it is a 5.6 GB file.

The Q8_0 file is 9.5 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 Q2_K at 3.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters8.95B
Layers33
Trained context262,144 tokens
KV cache (fp16)132 KB per token

Source

Quantized byIndexTeam
FamilyIndex
Licenseapache-2.0
Downloads (HF)1,551
Last updated2026-10-18

Frequently asked questions about Index Echo S2ST 9B

How much VRAM does Index Echo S2ST 9B need?

About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 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 Echo S2ST 9B on an 8 GB GPU?

Yes, with Q5_K_S: the 6.3 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Index Echo S2ST 9B GGUF?

It depends on the quant: Q2_K is 3.8 GB, Q3_K_S is 4.3 GB, Q3_K_M is 4.6 GB, Q3_K_L is 4.9 GB, IQ4_XS is 5.2 GB, Q4_K_S is 5.4 GB and 6 more.

What context length does Index Echo S2ST 9B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.

Where can I download Index Echo S2ST 9B GGUF?

The files are on Hugging Face in the IndexTeam/Index-Echo-S2ST-9B-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 Echo S2ST 9B 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 Index Echo S2ST 9B on 8 GB VRAM?

Yes, using Q4_K_M or Q5_K_S quantizations will fit within 8 GB VRAM with approximate 7–8 GB memory usage.

Does the GGUF package include the audio synthesis part?

No, the GGUF contains only the text LLM backbone. The full speech pipeline is not supported by llama.cpp.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from IndexTeam

All by IndexTeam →

More Index models

All Index →

Other small models

All small models →