QW

silicon based girlfriend v2

QwenGGUF by RX5950XTUpdated 2026-09-17
Download on Hugging Face
Parameters9.2B
Context256K
Layers33
Architectureqwen35
Smallest quant0.0 GB
Quick answer

silicon based girlfriend v2 needs about 7.4 GB of memory at Q4_K_M (a 5.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 0.0 GB to 9.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

Silicon Based Girlfriend v2 – a 9.2B Qwen3.5‑based roleplay model

Silicon Based Girlfriend v2 is a 9.2B‑parameter Qwen3.5 model fine‑tuned for long‑form roleplay. It supports vision and is released under Apache‑2.0. The model is trained on synthetic data and is intended for research use only.

Good at

  • Long‑form roleplay with consistent character
  • Vision support for basic image understanding
  • Low‑refusal generation

Limits

  • Not suitable for fact checking or math
  • Contains adult content – not for minors
  • Requires 8K context for Q4_K_M

Best for

  • Interactive roleplay sessions
  • Creative writing with visual prompts
  • Research on conversational consistency

Who it’s for. Developers and researchers who need a 9B‑parameter Qwen3.5 variant for roleplay and vision tasks. The model is not intended for production or public deployment due to limited safety filtering.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.6 GB
Fits Get file →
Q4_K_M5.8 GB 7.4 GB
Tight Get file →
Q8_09.8 GB 11.4 GB
Too big Get file →

For 8 GB VRAM use the Q4_K_M file (5.78 GB, ~7.4 GB memory at 8K context). For 12 GB VRAM the Q8_0 file (9.79 GB, ~11.4 GB memory) provides higher precision. The unknown quant file is very small but memory usage is not specified.

What GPU do you need for silicon based girlfriend 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: the best quant that fits is the main file (0.0 GB file, about 1.6 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (5.8 GB file, about 7.4 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 11.4 GB in use).

Which silicon based girlfriend v2 quant should you choose?

Q4_K_M is the usual starting point for silicon based girlfriend v2: it balances file size and quality well. Here it is a 5.8 GB file.

The Q8_0 file is 9.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters9.2B
Layers33
Trained context262,144 tokens
KV cache (fp16)132 KB per token

Source

Quantized byRX5950XT
FamilyQwen
Licenseapache-2.0
Downloads (HF)5,753
Last updated2026-09-17

Frequently asked questions about silicon based girlfriend v2

How much VRAM does silicon based girlfriend v2 need?

About 7.4 GB at Q4_K_M with an 8K context window. That is the 5.8 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 silicon based girlfriend v2 on an 8 GB GPU?

Yes, with Q4_K_M: the 5.8 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of silicon based girlfriend v2 GGUF?

It depends on the quant: file is 0.0 GB, Q4_K_M is 5.8 GB, Q8_0 is 9.8 GB.

What context length does silicon based girlfriend v2 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.

Where can I download silicon based girlfriend v2 GGUF?

The files are on Hugging Face in the RX5950XT/silicon-based-girlfriend-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 silicon based girlfriend 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?

Yes, the Q4_K_M quantized model fits on 8 GB VRAM with an estimated 7.4 GB memory usage at 8K context.

Is this model safe for public use?

No. The model has reduced safety filtering and may produce adult or inappropriate content. Use only in controlled environments.

Does it support vision?

Yes, it includes vision capabilities but only basic image understanding; it may misread two‑digit numbers.

Other GGUFs of Huihui-Qwen3.5-9B-abliterated

Similar models

Browse all →

More from RX5950XT

All by RX5950XT →

More Qwen models

All Qwen →

Other small models

All small models →