ru uncensored v2 needs about 9.3 GB of memory at Q4_K_M (a 7.5 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 5.4 GB.
12.2B Russian uncensored Llama model for local inference
ru uncensored v2 is a 12.2B parameter Llama model optimized for local inference via GGUF. It supports Russian and partial English and is designed for research, testing, and safety evaluation in controlled environments.
Good at
- Russian roleplay
- Local inference
- Research experiments
Limits
- May generate unsafe content
- Not for public production
- Requires external guardrails
Best for
- Closed‑stand prototyping
- Safety boundary testing
- Local chat experiments
Who it’s for. Engineers and researchers who need a Russian‑language LLM for local testing and safety research. The model is intended for controlled environments and should be paired with external moderation and guardrails.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 7.5 GB | 9.3 GB | Too big | Get file → |
The Q4_K_M quant is 7.48 GB and requires about 9.3 GB of VRAM at 8 k context. This is the only quant available, so use it if your GPU can accommodate the memory estimate. For smaller GPUs, consider a different quant if available.
What GPU do you need for ru uncensored v2?
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 Q4_K_M (7.5 GB file, about 9.3 GB in use).
Which ru uncensored v2 quant should you choose?
Q4_K_M is the usual starting point for ru uncensored v2: it balances file size and quality well. Here it is a 7.5 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about ru uncensored v2
How much VRAM does ru uncensored v2 need?
About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.5 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 ru uncensored v2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of ru uncensored v2 GGUF?
It depends on the quant: Q4_K_M is 7.5 GB.
What context length does ru uncensored v2 support?
The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download ru uncensored v2 GGUF?
The files are on Hugging Face in the aiplatforms/ru-uncensored-v2-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 ru uncensored v2 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 this model on 8 GB VRAM?
The Q4_K_M quant needs about 9.3 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does this model support vision?
No, it is a text‑only model.
Is it safe for production use?
No, it requires external guardrails and is not suitable for public production.