GR

Granite Speech 5.0 470M TurboCTC

GraniteGGUF by handy-computerUpdated 2026-10-16
Download on Hugging Face
Parameters473M
Context—
Layers—
Architecturegranite_speech5_ctc
Smallest quant0.3 GB
Quick answer

Granite Speech 5.0 470M TurboCTC needs about 0.8 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.3 GB (Q4_K_M) to 0.9 GB (F16).

Granite Speech 5.0 470M TurboCTC – compact multilingual ASR

Granite Speech 5.0 470M TurboCTC is a 470 million parameter multilingual ASR model. It supports English, French, German, Spanish, Portuguese, Italian and Japanese with native punctuation and capitalization. The model is optimized for low‑latency inference on edge devices.

Good at

  • Fast inference on laptops and smartphones
  • Multilingual transcription with punctuation
  • Low‑memory footprint

Limits

  • No vision support
  • Limited to 8 k context
  • Requires 16 kHz mono WAV

Best for

  • Edge device speech recognition
  • Multilingual customer support bots
  • Transcription of short audio clips

Who it’s for. Developers building enterprise applications that need accurate, low‑latency, multilingual speech-to-text on resource‑constrained hardware. The model is released under Apache 2.0 and is suitable for commercial use.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.3 GB 0.8 GB
Fits Get file →
Q5_K_M0.3 GB 0.9 GB
Fits Get file →
Q6_K0.4 GB 0.9 GB
Fits Get file →
Q8_00.5 GB 1.1 GB
Fits Get file →
BF160.9 GB 1.6 GB
Fits Get file →
F160.9 GB 1.6 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.28 GB file, 0.8 GB memory at 8 k context). If 12 GB VRAM is available, Q5_K_M (0.34 GB, 0.9 GB memory) offers a balance of speed and quality. For higher precision, Q8_0 (0.51 GB, 1.1 GB memory) can be used on GPUs with 16 GB VRAM.

What GPU do you need for Granite Speech 5.0 470M TurboCTC?

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 BF16 (0.9 GB file, about 1.6 GB in use).

Which Granite Speech 5.0 470M TurboCTC quant should you choose?

Q4_K_M is the usual starting point for Granite Speech 5.0 470M TurboCTC: it balances file size and quality well. Here it is a 0.3 GB file.

The Q8_0 file is 0.5 GB, about 1.8 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegranite_speech5_ctc
Parameters473M

Source

Quantized byhandy-computer
FamilyGranite
Licenseapache-2.0
Downloads (HF)1,518
Last updated2026-10-16

Frequently asked questions about Granite Speech 5.0 470M TurboCTC

How much VRAM does Granite Speech 5.0 470M TurboCTC need?

About 0.8 GB at Q4_K_M with an 8K context window. That is the 0.3 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 Granite Speech 5.0 470M TurboCTC on an 8 GB GPU?

Yes, with BF16: the 0.9 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite Speech 5.0 470M TurboCTC GGUF?

It depends on the quant: Q4_K_M is 0.3 GB, Q5_K_M is 0.3 GB, Q6_K is 0.4 GB, Q8_0 is 0.5 GB, BF16 is 0.9 GB, F16 is 0.9 GB.

Where can I download Granite Speech 5.0 470M TurboCTC GGUF?

The files are on Hugging Face in the handy-computer/granite-speech-5.0-470m-turboctc-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 Granite Speech 5.0 470M TurboCTC 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 Granite Speech 5.0 470M TurboCTC on 8 GB VRAM?

Yes, the Q4_K_M quantized file is 0.28 GB and requires about 0.8 GB VRAM at 8 k context.

Does the model support streaming inference?

No, the model is non‑streaming and uses greedy CTC decoding.

What languages are supported?

English, French, German, Spanish, Portuguese, Italian and Japanese.

Other GGUFs of granite-speech-5.0-470m-turboctc

Similar models

Browse all →

More from handy-computer

All by handy-computer →

More Granite models

All Granite →

Other tiny models

All tiny models →