Fwizzer-R1-3B needs about 3.5 GB of memory at its main file (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 2.1 GB to 3.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 3.5 GB.
Fwizzer-R1-3B-RU: a 3.43B Russian reasoning model
Fwizzer-R1-3B-RU is a 3.43B parameter model built on the mistral3 architecture. It is trained for step‑by‑step reasoning on a curated Russian dataset. The model is released under the apache-2.0 license.
Good at
- Reasoning
- Russian language
- Step‑by‑step dialogue
Limits
- No vision support
- Large context requires high VRAM
- License requires attribution
Best for
- Chatbots needing logical flow
- Educational tutoring in Russian
- Research on CoT reasoning
Who it’s for. Developers building Russian language applications that require logical reasoning. Researchers interested in step‑by‑step dialogue models. Teams needing an open‑source, apache‑licensed model for integration into local inference pipelines.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2.1 GB | 3.5 GB | Fits | Get file → | |
| — | 3.7 GB | 5.0 GB | Fits | Get file → |
For 8 GB VRAM use the 2.15 GB file; it requires about 3.5 GB memory at 8 k context. For 12 GB VRAM use the 3.65 GB file; it needs about 5 GB memory at 8 k context. Memory estimates are approximate.
What GPU do you need for Fwizzer-R1-3B?
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 the main file (2.1 GB file, about 3.5 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (3.7 GB file, about 5.0 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Fwizzer-R1-3B
How much VRAM does Fwizzer-R1-3B need?
About 3.5 GB at its main file with an 8K context window. That is the 2.1 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 Fwizzer-R1-3B on an 8 GB GPU?
Yes, with the smaller files: 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 Fwizzer-R1-3B GGUF?
It depends on the quant: file is 2.1 GB, file is 3.7 GB.
What context length does Fwizzer-R1-3B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). 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 Fwizzer-R1-3B GGUF?
The files are on Hugging Face in the fwizzer1/Fwizzer-R1-3B-RU repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Fwizzer-R1-3B 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 Fwizzer-R1-3B-RU on 8 GB VRAM?
Yes, the 2.15 GB GGUF file uses about 3.5 GB memory at 8 k context, fitting within 8 GB VRAM.
Does the model support vision tasks?
No, the model has no vision capabilities.
What license does the model use?
The model is released under the apache-2.0 license.