RusMind 4.5 Vspyshka needs about 17.0 GB of memory at BF16 (a 15.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
RusMind 4.5 Vspyshka – 7.52B gemma4 model for reasoning and tool use
RusMind 4.5 Vspyshka is a 7.52 billion‑parameter gemma4 architecture model. It supports reasoning and tool usage. The model is available in a BF16 quantized GGUF file.
Good at
- Reasoning
- Tool usage
- Bilingual Russian and English
Limits
- No vision support
- Requires 17 GB VRAM at 8 k context
- License type is other
Best for
- Chatting in Russian and English
- Coding assistance
- Educational explanations
Who it’s for. Developers and researchers needing a medium‑size LLM for reasoning tasks in Russian and English. The model is suitable for local deployment without internet access.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 15.1 GB | 17.0 GB | Too big | Get file → |
The only available quant is BF16, 15.05 GB file size. It requires approximately 17 GB VRAM at 8 k context. For lower VRAM budgets, no other quant is available.
What GPU do you need for RusMind 4.5 Vspyshka?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is BF16 (15.1 GB file, about 17.0 GB in use).
Which RusMind 4.5 Vspyshka quant should you choose?
BF16 (15.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about RusMind 4.5 Vspyshka
How much VRAM does RusMind 4.5 Vspyshka need?
About 17.0 GB at BF16 with an 8K context window. That is the 15.1 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 RusMind 4.5 Vspyshka on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of RusMind 4.5 Vspyshka GGUF?
It depends on the quant: BF16 is 15.1 GB.
What context length does RusMind 4.5 Vspyshka 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 4.5 Vspyshka GGUF?
The files are on Hugging Face in the DICPlay/RusMind-4.5-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 4.5 Vspyshka 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 this model on 8 GB VRAM?
No, the BF16 quant requires about 17 GB VRAM at 8 k context.
Does it support vision tasks?
No, the model has no vision capability.
What languages does it understand?
It supports Russian and English.