GI

GigaAM v3 CTC

GigaamGGUF by handy-computerUpdated 2026-10-16
Download on Hugging Face
Parameters221M
Context—
Layers—
Architecturegigaam
Smallest quant0.2 GB
Quick answer

GigaAM v3 CTC needs about 0.7 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.2 GB (Q4_K_M) to 0.9 GB (F32).

GigaAM v3 CTC – 220 M‑parameter Russian ASR model in GGUF format

GigaAM v3 CTC is a Conformer‑based ASR model with 220 M parameters. It is trained on diverse Russian speech data using a HuBERT‑CTC objective and outputs lowercased Russian text without punctuation. The model is available in several GGUF quantizations for efficient inference.

Good at

  • Accurate Russian speech recognition
  • Low‑latency inference on modest GPUs
  • Supports greedy CTC decoding

Limits

  • No punctuation or text normalization
  • Requires 16 kHz mono WAV input
  • No vision or multimodal support

Best for

  • Transcribing Russian audio files
  • Real‑time voice‑to‑text on edge devices
  • Batch processing of Russian speech datasets

Who it’s for. Developers building Russian speech‑to‑text pipelines who need a lightweight, open‑source model. The MIT license allows free use in commercial and research projects.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.2 GB 0.7 GB
Fits Get file →
Q5_K_M0.2 GB 0.7 GB
Fits Get file →
Q6_K0.2 GB 0.8 GB
Fits Get file →
Q8_00.3 GB 0.8 GB
Fits Get file →
F160.4 GB 1.0 GB
Fits Get file →
F320.9 GB 1.5 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M or Q5_K_M (≈0.18–0.20 GB) are suitable, using about 0.7 GB of VRAM at 8 k context. If more VRAM is available, Q6_K or Q8_0 (≈0.23–0.27 GB) give slightly higher precision. Full‑precision F16 or F32 can be used on systems with ≥1 GB VRAM.

What GPU do you need for GigaAM v3 CTC?

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 F32 (0.9 GB file, about 1.5 GB in use).

Which GigaAM v3 CTC quant should you choose?

Q4_K_M is the usual starting point for GigaAM v3 CTC: it balances file size and quality well. Here it is a 0.2 GB file.

The Q8_0 file is 0.3 GB, about 1.5 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

Architecturegigaam
Parameters221M

Source

Quantized byhandy-computer
FamilyGigaam
Licensemit
Downloads (HF)12,330
Last updated2026-10-16

Frequently asked questions about GigaAM v3 CTC

How much VRAM does GigaAM v3 CTC need?

About 0.7 GB at Q4_K_M with an 8K context window. That is the 0.2 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 GigaAM v3 CTC on an 8 GB GPU?

Yes, with F32: the 0.9 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of GigaAM v3 CTC GGUF?

It depends on the quant: Q4_K_M is 0.2 GB, Q5_K_M is 0.2 GB, Q6_K is 0.2 GB, Q8_0 is 0.3 GB, F16 is 0.4 GB, F32 is 0.9 GB.

Where can I download GigaAM v3 CTC GGUF?

The files are on Hugging Face in the handy-computer/gigaam-v3-ctc-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 GigaAM v3 CTC use?

Hugging Face lists the license as mit. 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 GigaAM v3 CTC on 8 GB VRAM?

Yes, the Q4_K_M and Q5_K_M quantizations use about 0.7 GB of VRAM at 8 k context, well within an 8 GB budget.

Does the model support punctuation?

No. The CTC decoder outputs lowercased Russian text without punctuation or text normalization.

What audio format is required?

The model expects 16 kHz mono WAV files; other formats must be converted before inference.

Other GGUFs of GigaAM-v3

Similar models

Browse all →

More from handy-computer

All by handy-computer →

More Gigaam models

All Gigaam →

Other tiny models

All tiny models →