PA

MS3.2 PaintedFantasy Visage v2 33B

PaintedfantasyGGUF by mradermacherUpdated 2025-12-25
Download on Hugging Face
Parameters33.6B
Context128K
Layers58
Architecturellama
Smallest quant0.0 GB
Quick answer

MS3.2 PaintedFantasy Visage v2 33B needs about 22.8 GB of memory at Q4_K_M (a 20.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 27.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 7.8 GB.

MS3.2 PaintedFantasy Visage v2 33B – 33.6B llama model for roleplay

MS3.2 PaintedFantasy Visage v2 33B is a 33.6B parameter llama architecture model. It supports a 131072 token context window and is licensed under apache-2.0. The model is optimized for roleplay scenarios.

Good at

  • Roleplay dialogue
  • Creative storytelling
  • Character interaction

Limits

  • Large memory requirement for full precision
  • No vision or multimodal support
  • Requires GGUF format

Best for

  • Chatbot development
  • Interactive fiction
  • Narrative generation

Who it’s for. Developers building conversational agents that need deep roleplay capabilities. Researchers exploring large context language models may also find this model useful.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.5 GB
Fits Get file →
IQ1_S7.3 GB 9.8 GB
Too big Get file →
IQ1_M8.0 GB 10.5 GB
Too big Get file →
IQ2_XXS9.2 GB 11.6 GB
Too big Get file →
IQ2_XS10.1 GB 12.6 GB
Too big Get file →
IQ2_S10.5 GB 12.9 GB
Too big Get file →
IQ2_M11.4 GB 13.9 GB
Too big Get file →
Q2_K_S11.7 GB 14.2 GB
Too big Get file →
Q2_K12.5 GB 15.0 GB
Too big Get file →
IQ3_XXS13.1 GB 15.6 GB
Too big Get file →
IQ3_XS14.0 GB 16.4 GB
Too big Get file →
Q3_K_S14.7 GB 17.1 GB
Too big Get file →
IQ3_S14.7 GB 17.2 GB
Too big Get file →
IQ3_M15.1 GB 17.5 GB
Too big Get file →
Q3_K_M16.3 GB 18.7 GB
Too big Get file →
Q3_K_L17.6 GB 20.0 GB
Too big Get file →
IQ4_XS18.1 GB 20.5 GB
Too big Get file →
Q4_019.1 GB 21.6 GB
Too big Get file →
Q4_K_S19.2 GB 21.7 GB
Too big Get file →
Q4_K_M20.4 GB 22.8 GB
Too big Get file →
Q4_121.1 GB 23.6 GB
Too big Get file →
Q5_K_S23.2 GB 25.6 GB
Too big Get file →
Q5_K_M23.8 GB 26.3 GB
Too big Get file →
Q6_K27.6 GB 30.0 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (7.33 GB file, 9.8 GB memory at 8k context). For 12 GB VRAM, IQ2_XS (10.14 GB file, 12.6 GB memory). For 16 GB VRAM, Q3_K_S (14.7 GB file, 17.1 GB memory). Memory estimates are approximate.

What GPU do you need for MS3.2 PaintedFantasy Visage v2 33B?

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 2.5 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.5 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.5 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_XXS (9.2 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (13.1 GB file, about 15.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (21.1 GB file, about 23.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (27.6 GB file, about 30.0 GB in use).

Which MS3.2 PaintedFantasy Visage v2 33B quant should you choose?

Q4_K_M is the usual starting point for MS3.2 PaintedFantasy Visage v2 33B: it balances file size and quality well. Here it is a 20.4 GB file.

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

Architecturellama
Parameters33.6B
Layers58
Trained context131,072 tokens
KV cache (fp16)232 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)741
Last updated2025-12-25

Frequently asked questions about MS3.2 PaintedFantasy Visage v2 33B

How much VRAM does MS3.2 PaintedFantasy Visage v2 33B need?

About 22.8 GB at Q4_K_M with an 8K context window. That is the 20.4 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 MS3.2 PaintedFantasy Visage v2 33B on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MS3.2 PaintedFantasy Visage v2 33B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 7.3 GB, IQ1_M is 8.0 GB, IQ2_XXS is 9.2 GB, IQ2_XS is 10.1 GB, IQ2_S is 10.5 GB and 18 more.

What context length does MS3.2 PaintedFantasy Visage v2 33B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.8 GB at 32K.

Where can I download MS3.2 PaintedFantasy Visage v2 33B GGUF?

The files are on Hugging Face in the mradermacher/MS3.2-PaintedFantasy-Visage-v2-33B-i1-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 MS3.2 PaintedFantasy Visage v2 33B 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 MS3.2 PaintedFantasy Visage v2 33B on 8 GB VRAM?

Use the IQ1_S quant, which is 7.33 GB in size and requires about 9.8 GB of VRAM at 8k context.

Does this model support vision or image inputs?

No, the model only handles text and has no vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of MS3.2-PaintedFantasy-Visage-v2-33B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Paintedfantasy models

All Paintedfantasy →

Other medium models

All medium models →