Voxtral Mini 4B Realtime Estonian 2609 needs about 3.5 GB of memory at Q4_K_M (a 2.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.5 GB (Q2_K) to 6.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.5 GB.
Voxtral Mini 4B Realtime Estonian 2609 – Estonian ASR with vision support
Voxtral Mini 4B Realtime Estonian 2609 is a 3.43B‑parameter model fine‑tuned for Estonian speech recognition. It streams partial transcripts while audio arrives, suitable for live subtitling and voice interfaces. The model includes a 970M‑parameter audio encoder and a multimodal projector.
Good at
- Real‑time Estonian ASR
- Causal streaming transcription
- Vision‑enabled multimodal tasks
Limits
- No vision support beyond basic detection
- Requires mono 16 kHz audio
- License is apache‑2.0
Best for
- Live meeting transcription
- Real‑time subtitle generation
- Voice‑controlled Estonian applications
Who it’s for. Developers building Estonian speech‑to‑text services or multimodal applications that need instant transcription. The model is ideal for low‑latency environments where partial outputs are required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.5 GB | 2.8 GB | Fits | Get file → | |
| Q3_K_S | 1.6 GB | 3.0 GB | Fits | Get file → | |
| Q3_K_M | 1.8 GB | 3.2 GB | Fits | Get file → | |
| Q3_K_L | 1.9 GB | 3.3 GB | Fits | Get file → | |
| IQ4_XS | 2.0 GB | 3.3 GB | Fits | Get file → | |
| Q4_K_S | 2.1 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_M | 2.2 GB | 3.5 GB | Fits | Get file → | |
| Q5_K_S | 2.4 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_M | 2.5 GB | 3.9 GB | Fits | Get file → | |
| Q6_K | 2.8 GB | 4.2 GB | Fits | Get file → | |
| Q8_0 | 3.7 GB | 5.0 GB | Fits | Get file → | |
| F16 | 6.9 GB | 8.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (2.15 GB file, ~3.5 GB memory at 8k context). If 4 GB VRAM is available, Q3_K_M (1.8 GB file, ~3.2 GB memory) is a good balance. For minimal memory, Q2_K (1.46 GB file, ~2.8 GB memory) fits 4 GB VRAM but may reduce quality.
What GPU do you need for Voxtral Mini 4B Realtime Estonian 2609?
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 Q5_K_M (2.5 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.7 GB file, about 5.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.7 GB file, about 5.0 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (6.9 GB file, about 8.2 GB in use).
Which Voxtral Mini 4B Realtime Estonian 2609 quant should you choose?
Q4_K_M is the usual starting point for Voxtral Mini 4B Realtime Estonian 2609: it balances file size and quality well. Here it is a 2.2 GB file.
The Q8_0 file is 3.7 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 1.5 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
Frequently asked questions about Voxtral Mini 4B Realtime Estonian 2609
How much VRAM does Voxtral Mini 4B Realtime Estonian 2609 need?
About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.2 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 Voxtral Mini 4B Realtime Estonian 2609 on an 8 GB GPU?
Yes, with Q8_0: the 3.7 GB file needs about 5.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Voxtral Mini 4B Realtime Estonian 2609 GGUF?
It depends on the quant: Q2_K is 1.5 GB, Q3_K_S is 1.6 GB, Q3_K_M is 1.8 GB, Q3_K_L is 1.9 GB, IQ4_XS is 2.0 GB, Q4_K_S is 2.1 GB and 6 more.
What context length does Voxtral Mini 4B Realtime Estonian 2609 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.5 GB at 32K.
Where can I download Voxtral Mini 4B Realtime Estonian 2609 GGUF?
The files are on Hugging Face in the mradermacher/Voxtral-Mini-4B-Realtime-estonian-2609-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 Voxtral Mini 4B Realtime Estonian 2609 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 Voxtral Mini 4B Realtime Estonian 2609 on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 3.5 GB memory at 8k context, fitting within 8 GB VRAM.
Does the model support other languages besides Estonian?
The model is fine‑tuned for Estonian; other languages are not guaranteed to perform well.
What audio format does the model require?
It expects mono, 16 kHz audio; callers should downmix and resample input as needed.