RusMind 4.5 Momentum needs about 10.4 GB of memory at BF16 (a 9.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.
RusMind 4.5 Momentum – lightweight Gemma4 model for local use
RusMind 4.5 Momentum is a 4.65 billion‑parameter Gemma4 model. It supports reasoning and tools. The BF16 quantized file is 9.31 GB and requires about 10.4 GB of VRAM at 8 k context.
Good at
- Reasoning
- Tools integration
- Local deployment
Limits
- No vision support
- License type is other
- Requires 10.4 GB VRAM for 8 k context
Best for
- Running on laptops
- Offline chat assistants
- Educational tutoring
Who it’s for. Developers and researchers who need a small, local LLM with reasoning capabilities. The model runs on standard PCs and phones without internet access.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 9.3 GB | 10.4 GB | Too big | Get file → |
The only available quant is BF16, 9.31 GB. It needs roughly 10.4 GB VRAM at 8 k context. If you have less than 10 GB VRAM, the model will not run. For larger VRAM budgets, BF16 is the recommended choice.
What GPU do you need for RusMind 4.5 Momentum?
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: the best quant that fits is BF16 (9.3 GB file, about 10.4 GB in use).
Which RusMind 4.5 Momentum quant should you choose?
BF16 (9.3 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 Momentum
How much VRAM does RusMind 4.5 Momentum need?
About 10.4 GB at BF16 with an 8K context window. That is the 9.3 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 4.5 Momentum on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of RusMind 4.5 Momentum GGUF?
It depends on the quant: BF16 is 9.3 GB.
What context length does RusMind 4.5 Momentum support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.3 GB at 32K.
Where can I download RusMind 4.5 Momentum GGUF?
The files are on Hugging Face in the DICPlay/RusMind-4.5-Momentum 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 Momentum 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 4.5 Momentum on 8 GB VRAM?
No. The BF16 quant requires about 10.4 GB VRAM at 8 k context, so 8 GB is insufficient.
Does the model support vision tasks?
No. The model has no vision capabilities.
What languages does it support?
The model supports Russian and English.