Girlfriend needs about 3.5 GB of memory at Q4_K_M (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 (Q4_K_M) to 6.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.5 GB.
Girlfriend – a 3.4B Mistral3 model finetuned for roleplay
Girlfriend is a 3.4B parameter Mistral3 model finetuned with LoRA for conversational roleplay. It is based on unsloth/Ministral-3-3B-Instruct-2512 and released under Apache‑2.0. The model supports a 262144 token context window.
Good at
- Roleplay conversations
- Persona‑style chat
- Single‑turn Q&A
Limits
- No vision support
- Large context window requires significant VRAM
- No multilingual data listed
Best for
- Personal companion chat
- On‑device roleplay bots
- Testing LoRA finetunes
Who it’s for. Developers and hobbyists who want a small, open‑source model for roleplay or companion chat. The model is suitable for local deployment on hardware with enough VRAM to handle the 3.4B parameters.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.1 GB | 3.5 GB | Fits | Get file → | |
| F16 | 6.9 GB | 8.2 GB | Too big | Get file → |
For 8 GB VRAM use the Q4_K_M quantized file (2.15 GB, ~3.5 GB memory at 8 k context). For higher precision and more memory use the F16 file (6.87 GB, ~8.2 GB memory at 8 k context).
What GPU do you need for Girlfriend?
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 Q4_K_M (2.1 GB file, about 3.5 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_M (2.1 GB file, about 3.5 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_K_M (2.1 GB file, about 3.5 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (6.9 GB file, about 8.2 GB in use).
Which Girlfriend quant should you choose?
Q4_K_M is the usual starting point for Girlfriend: it balances file size and quality well. Here it is a 2.1 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Girlfriend
How much VRAM does Girlfriend need?
About 3.5 GB at Q4_K_M 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 Girlfriend on an 8 GB GPU?
Yes, with Q4_K_M: the 2.1 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Girlfriend GGUF?
It depends on the quant: Q4_K_M is 2.1 GB, F16 is 6.9 GB.
What context length does Girlfriend 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 Girlfriend GGUF?
The files are on Hugging Face in the nachiketj14/Girlfriend repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Girlfriend 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 Girlfriend on 8 GB VRAM?
Yes, the Q4_K_M quantized version is 2.15 GB and requires about 3.5 GB of VRAM at 8 k context.
Does Girlfriend support images?
No, Girlfriend is a text‑only model and does not have vision capabilities.