Thaki ASR KO Dialects v1 needs about 2.5 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.8 GB (Q2_K) to 3.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Thaki ASR KO Dialects v1 – 1.72B Qwen3VL ASR fine‑tuned on Korean dialects
Thaki ASR KO Dialects v1 is a 1.72B parameter Qwen3VL model fine‑tuned on five Korean regional dialects. It retains standard Korean performance while improving dialect transcription. The model is released under Apache‑2.0 and supports vision tasks.
Good at
- Dialect‑specific Korean ASR
- Standard Korean ASR
- Vision‑enabled ASR
Limits
- No non‑Korean language evaluation
- Not validated for noisy or far‑field audio
- No production‑grade guarantees
Best for
- Transcribing Korean regional dialects
- Research on Korean ASR
- Integrating vision‑enabled ASR in prototypes
Who it’s for. Researchers and developers needing Korean dialect transcription. Suitable for academic projects and prototype development where experimental models are acceptable.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.8 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_S | 0.9 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_M | 0.9 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_L | 1.0 GB | 2.4 GB | Fits | Get file → | |
| IQ4_XS | 1.0 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_S | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q5_K_S | 1.2 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_M | 1.3 GB | 2.7 GB | Fits | Get file → | |
| Q6_K | 1.4 GB | 2.9 GB | Fits | Get file → | |
| Q8_0 | 1.8 GB | 3.3 GB | Fits | Get file → | |
| F16 | 3.4 GB | 4.9 GB | Fits | Get file → |
For 8 GB VRAM use Q4_K_M (1.11 GB, ~2.5 GB memory). For 12 GB VRAM use Q5_K_M (1.26 GB, ~2.7 GB memory). For 16 GB VRAM use Q6_K (1.42 GB, ~2.9 GB memory).
What GPU do you need for Thaki ASR KO Dialects v1?
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: the best quant that fits is Q8_0 (1.8 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (3.4 GB file, about 4.9 GB in use).
Which Thaki ASR KO Dialects v1 quant should you choose?
Q4_K_M is the usual starting point for Thaki ASR KO Dialects v1: it balances file size and quality well. Here it is a 1.1 GB file.
The Q8_0 file is 1.8 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 0.8 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
Source
Frequently asked questions about Thaki ASR KO Dialects v1
How much VRAM does Thaki ASR KO Dialects v1 need?
About 2.5 GB at Q4_K_M with an 8K context window. That is the 1.1 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 Thaki ASR KO Dialects v1 on an 8 GB GPU?
Yes, with F16: the 3.4 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Thaki ASR KO Dialects v1 GGUF?
It depends on the quant: Q2_K is 0.8 GB, Q3_K_S is 0.9 GB, Q3_K_M is 0.9 GB, Q3_K_L is 1.0 GB, IQ4_XS is 1.0 GB, Q4_K_S is 1.1 GB and 6 more.
What context length does Thaki ASR KO Dialects v1 support?
The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download Thaki ASR KO Dialects v1 GGUF?
The files are on Hugging Face in the mradermacher/Thaki-ASR-KO-Dialects-v1-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 Thaki ASR KO Dialects v1 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 this model on 8 GB VRAM?
Yes, the Q4_K_M quant file is 1.11 GB and requires about 2.5 GB of VRAM at 8 k context.
Does the model support English?
The model accepts the base model’s 51 languages, but only Korean dialects were evaluated.
Is this model production ready?
No, it is a research‑gate release and has not been validated for noisy or far‑field audio.