GigaAM v3 E2E-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 E2E-CTC: 220‑M parameter Russian ASR in GGUF format
GigaAM v3 E2E-CTC is a 220‑million parameter Conformer model for Russian speech recognition. It outputs punctuated, normalized text directly using a CTC decoder. The model is licensed under MIT and available in several GGUF quantizations.
Good at
- End‑to‑end Russian ASR
- Punctuated, normalized output
- Low‑latency decoding
Limits
- No vision support
- Requires 8‑k context for memory estimates
- No external LM needed
Best for
- Transcribing Russian podcasts
- Voice‑to‑text for call centers
- Batch processing of Russian audio
Who it’s for. Developers building Russian speech‑to‑text pipelines who need a lightweight, offline model. The GGUF format allows deployment with transcribe.cpp on a range of hardware.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q5_K_M | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q6_K | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q8_0 | 0.3 GB | 0.8 GB | Fits | Get file → | |
| F16 | 0.4 GB | 1.0 GB | Fits | Get file → | |
| F32 | 0.9 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 ~0.7 GB at 8 k context. If more precision is needed and memory allows, Q6_K or Q8_0 (0.23–0.27 GB) are options. F16 and F32 provide higher quality at 0.45–0.88 GB.
What GPU do you need for GigaAM v3 E2E-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 E2E-CTC quant should you choose?
Q4_K_M is the usual starting point for GigaAM v3 E2E-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
Source
Frequently asked questions about GigaAM v3 E2E-CTC
How much VRAM does GigaAM v3 E2E-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 E2E-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 E2E-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 E2E-CTC GGUF?
The files are on Hugging Face in the handy-computer/gigaam-v3-e2e-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 E2E-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 E2E-CTC on 8 GB VRAM?
Yes, Q4_K_M or Q5_K_M quantizations fit within 8 GB VRAM, using about 0.7 GB at 8 k context.
Does the model support English speech?
No, the model is trained exclusively on Russian speech data.
Is an external language model required?
No, the model outputs punctuated, normalized text directly with greedy CTC decoding.