RA

raon speech 9b

RaonGGUF by cstrUpdated 2026-09-24
Download on Hugging Face
Parameters8.55B
Context—
Layers—
Architectureqwen3asr
Smallest quant5.0 GB
Quick answer

raon speech 9b needs about 10.7 GB of memory at Q8_0 (a 9.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 5.0 GB (Q4_K) to 17.1 GB (F16).

Raon Speech 9B – bilingual speech‑to‑text and text‑to‑speech model

Raon Speech 9B is an 8.55‑billion‑parameter multimodal model built on Qwen3 architecture. It supports English and Korean speech understanding, answering, and generation. The model is available in GGUF format with multiple quantizations.

Good at

  • Speech‑to‑text in English and Korean
  • Text‑to‑speech with speaker conditioning
  • Unified STT, TTS, TextQA, SpeechChat

Limits

  • No vision support
  • CC‑BY‑NC‑4.0 license – non‑commercial use only
  • Requires 8‑k context for estimates

Best for

  • Transcribing bilingual audio
  • Generating bilingual speech from text
  • Voice cloning with reference audio

Who it’s for. Developers building bilingual speech applications who need a single model for STT, TTS, and conversational tasks. The model is suitable for research and non‑commercial projects under the CC‑BY‑NC‑4.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K5.0 GB 6.1 GB
Fits Get file →
Q8_09.1 GB 10.7 GB
Too big Get file →
F1617.1 GB 19.7 GB
Too big Get file →

For 8‑GB VRAM, use Q4_K (file size 4.98 GB, estimated 6.1 GB memory). For 12‑GB VRAM, Q8_0 (9.09 GB, 10.7 GB memory). If more memory is available, F16 (17.1 GB, 19.7 GB) gives full precision.

What GPU do you need for raon speech 9b?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q4_K (5.0 GB file, about 6.1 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.1 GB file, about 10.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.1 GB file, about 10.7 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (17.1 GB file, about 19.7 GB in use).

Which raon speech 9b quant should you choose?

Q8_0 (9.1 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 5.0 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

Architectureqwen3asr
Parameters8.55B

Source

Quantized bycstr
FamilyRaon
Downloads (HF)950
Last updated2026-09-24

Frequently asked questions about raon speech 9b

How much VRAM does raon speech 9b need?

About 10.7 GB at Q8_0 with an 8K context window. That is the 9.1 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 raon speech 9b on an 8 GB GPU?

Yes, with Q4_K: 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 raon speech 9b GGUF?

It depends on the quant: Q4_K is 5.0 GB, Q8_0 is 9.1 GB, F16 is 17.1 GB.

Where can I download raon speech 9b GGUF?

The files are on Hugging Face in the cstr/raon-speech-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 raon speech 9b use?

Hugging Face lists the license as cc-by-nc-4.0. 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 Raon Speech 9B on 8 GB VRAM?

Yes, the Q4_K quantization requires about 6.1 GB of VRAM at 8‑k context, fitting within an 8‑GB GPU.

Does the model support Korean?

Yes, it is bilingual and supports speech understanding, answering, and generation in both English and Korean.

Is the model free for commercial use?

No, the CC‑BY‑NC‑4.0 license allows only non‑commercial use.

Similar models

Browse all →

More from cstr

All by cstr →

More Raon models

All Raon →

Other small models

All small models →