RusMind.Вспышка 3.2 needs about 7.2 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 5 quants, from 3.8 GB to 8.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
RusMind.Вспышка 3.2 – 7.52B‑parameter Gemma4 model for everyday Russian tasks
RusMind.Вспышка 3.2 is a 7.52 billion‑parameter Gemma4 model designed for everyday tasks such as writing, studying, and explanations. It supports reasoning and tool usage and runs offline on powerful PCs and flagship smartphones.
Good at
- Reasoning in Russian
- Tool integration
- Offline operation
Limits
- No vision support
- Requires large VRAM for full precision
- License is other
Best for
- Writing emails
- Explaining concepts
- Studying Russian culture
Who it’s for. Developers and users who need a Russian‑focused LLM that can run locally without internet. Ideal for applications requiring privacy and offline capability.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 3.8 GB | 5.7 GB | Fits | Get file → | |
| — | 3.8 GB (14 parts) | 5.7 GB | Fits | Get file → | |
| — | 4.2 GB | 6.1 GB | Fits | Get file → | |
| Q4_K_M | 5.3 GB | 7.2 GB | Tight | Get file → | |
| Q8_0 | 8.0 GB | 9.9 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (5.34 GB file, 7.2 GB memory at 8k context). For 12 GB VRAM use Q8_0 (8.03 GB file, 9.9 GB memory). Unknown quant files are larger and need more memory.
What GPU do you need for RusMind.Вспышка 3.2?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is the main file (3.8 GB file, about 5.7 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_K_M (5.3 GB file, about 7.2 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.9 GB in use).
Which RusMind.Вспышка 3.2 quant should you choose?
Q4_K_M is the usual starting point for RusMind.Вспышка 3.2: it balances file size and quality well. Here it is a 5.3 GB file.
The Q8_0 file is 8.0 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.
If memory is tight, the smallest file is the first one in the table at 3.8 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about RusMind.Вспышка 3.2
How much VRAM does RusMind.Вспышка 3.2 need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.3 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 RusMind.Вспышка 3.2 on an 8 GB GPU?
Yes, with Q4_K_M: the 5.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of RusMind.Вспышка 3.2 GGUF?
It depends on the quant: file is 3.8 GB, file is 3.8 GB, file is 4.2 GB, Q4_K_M is 5.3 GB, Q8_0 is 8.0 GB.
What context length does RusMind.Вспышка 3.2 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.
Where can I download RusMind.Вспышка 3.2 GGUF?
The files are on Hugging Face in the DICPlay/RusMind-3.2-Vspyshka repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does RusMind.Вспышка 3.2 use?
Hugging Face lists the license as other. 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 RusMind.Вспышка 3.2 on a GPU with 8 GB VRAM?
Yes, using the Q4_K_M quantized file (5.34 GB) which requires about 7.2 GB memory at 8k context. It fits within 8 GB VRAM with some headroom.
Does the model support vision tasks?
No, the model has no vision capabilities and is designed only for text.
What languages does the model understand?
The model is trained on Russian and English data and is optimized for Russian language tasks.