GI

ru girlfriend roleplay 1.5b gguf q8

GirlfriendGGUF by aiplatformsUpdated 2026-05-07
Download on Hugging Face
Parameters1.54B
Context32K
Layers28
Architectureqwen2
Smallest quant1.6 GB
Quick answer

ru girlfriend roleplay 1.5b gguf q8 needs about 2.4 GB of memory at Q8_0 (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

Russian girlfriend roleplay LLM for local dialogue prototypes

This 1.54B‑parameter Qwen2 model is tailored for Russian role‑play and female companion scenarios. It supports roleplay and tool usage in a local inference environment using GGUF format.

Good at

  • Russian roleplay
  • female companion dialogue
  • tool integration

Limits

  • No vision support
  • Requires guardrails for public use
  • Limited to local inference

Best for

  • Prototype local chatbots
  • Test emotional Russian dialogue
  • Develop female companion apps

Who it’s for. Developers building Russian‑language role‑play or companion chatbots who need a compact, local model. Suitable for controlled environments where external APIs are not desired.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_01.6 GB 2.4 GB
Fits Get file →

The Q8_0 quantization file is 1.65 GB and needs about 2.4 GB of VRAM at 8 k context. For 8 GB VRAM, this quant is suitable. If memory is tighter, a lower‑bit quant would be required, but none are listed.

What GPU do you need for ru girlfriend roleplay 1.5b gguf q8?

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 Q8_0 (1.6 GB file, about 2.4 GB in use).

Which ru girlfriend roleplay 1.5b gguf q8 quant should you choose?

Q8_0 (1.6 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters1.54B
Layers28
Trained context32,768 tokens
KV cache (fp16)28 KB per token

Source

Quantized byaiplatforms
Licenseapache-2.0
Downloads (HF)1,951
Last updated2026-05-07

Frequently asked questions about ru girlfriend roleplay 1.5b gguf q8

How much VRAM does ru girlfriend roleplay 1.5b gguf q8 need?

About 2.4 GB at Q8_0 with an 8K context window. That is the 1.6 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 girlfriend roleplay 1.5b gguf q8 on an 8 GB GPU?

Yes, with Q8_0: the 1.6 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ru girlfriend roleplay 1.5b gguf q8 GGUF?

It depends on the quant: Q8_0 is 1.6 GB.

What context length does ru girlfriend roleplay 1.5b gguf q8 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.

Where can I download ru girlfriend roleplay 1.5b gguf q8 GGUF?

The files are on Hugging Face in the aiplatforms/ru-girlfriend-roleplay-1.5b-gguf-q8 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 girlfriend roleplay 1.5b gguf q8 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?

Yes, the Q8_0 quant requires about 2.4 GB of VRAM at 8 k context, well within an 8 GB budget.

Does this model support English?

It is primarily Russian with partial English support, designed for Russian role‑play scenarios.

Is it safe for public deployment?

No. Public use requires guardrails, moderation, and security layers; it is not a general‑purpose assistant.

Similar models

Browse all →

More from aiplatforms

All by aiplatforms →

More Girlfriend models

All Girlfriend →

Other tiny models

All tiny models →