PA

MS3.2 PaintedFantasy Visage v3 34B

PaintedfantasyGGUF by bartowskiUpdated 2025-08-26
Download on Hugging Face
Parameters34B
Context128K
Layers59
Architecturellama
Smallest quant0.0 GB
Quick answer

MS3.2 PaintedFantasy Visage v3 34B needs about 23.2 GB of memory at Q4_K_M (a 20.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 28 quants, from 0.0 GB to 68.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 7.9 GB.

MS3.2 PaintedFantasy Visage v3 34B – a 34‑billion‑parameter Llama model

MS3.2 PaintedFantasy Visage v3 34B is a 34‑billion‑parameter Llama model trained on 131072 context tokens. It is available in multiple GGUF quantizations ranging from IQ2_XXS to Q8_0. The model is provided by bartowski and derived from zerofata/MS3.2-PaintedFantasy-Visage-v3-34B.

Good at

  • Large context generation
  • High‑capacity text modeling
  • Versatile language tasks

Limits

  • No vision support
  • License not specified
  • Large memory requirement for full precision

Best for

  • Research prototyping
  • Fine‑tuning on custom datasets
  • Long‑form content creation

Who it’s for. Researchers and developers needing a large Llama model for text generation and fine‑tuning. The model is suitable for environments that can handle high VRAM or RAM demands.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.5 GB
Fits Get file →
IQ2_XXS9.3 GB 11.8 GB
Too big Get file →
IQ2_XS10.3 GB 12.8 GB
Too big Get file →
IQ2_S10.7 GB 13.1 GB
Too big Get file →
IQ2_M11.6 GB 14.1 GB
Too big Get file →
Q2_K12.7 GB 15.2 GB
Too big Get file →
IQ3_XXS13.3 GB 15.8 GB
Too big Get file →
Q2_K_L13.4 GB 15.9 GB
Too big Get file →
IQ3_XS14.2 GB 16.7 GB
Too big Get file →
Q3_K_S14.9 GB 17.4 GB
Too big Get file →
IQ3_M15.3 GB 17.8 GB
Too big Get file →
Q3_K_M16.5 GB 19.0 GB
Too big Get file →
Q3_K_L17.9 GB 20.4 GB
Too big Get file →
IQ4_XS18.4 GB 20.9 GB
Too big Get file →
Q3_K_XL18.5 GB 21.0 GB
Too big Get file →
IQ4_NL19.4 GB 21.9 GB
Too big Get file →
Q4_019.5 GB 21.9 GB
Too big Get file →
Q4_K_S19.5 GB 22.0 GB
Too big Get file →
Q4_K_M20.7 GB 23.2 GB
Too big Get file →
Q4_K_L21.2 GB 23.7 GB
Too big Get file →
Q4_121.5 GB 24.0 GB
Too big Get file →
Q5_K_S23.6 GB 26.0 GB
Too big Get file →
Q5_K_M24.2 GB 26.7 GB
Too big Get file →
Q5_K_L24.6 GB 27.1 GB
Too big Get file →
Q6_K28.0 GB 30.5 GB
Too big Get file →
Q6_K_L28.3 GB 30.8 GB
Too big Get file →
Q8_036.3 GB 38.8 GB
Too big Get file →
BF1668.3 GB (2 parts) 70.8 GB
Too big Get file →

For 8‑GB VRAM, use IQ2_XXS (file size 9.32 GB, memory 11.8 GB at 8K context). For 16‑GB VRAM, IQ3_M (file size 15.3 GB, memory 17.8 GB) or Q4_K_M (file size 20.68 GB, memory 23.2 GB). For 24‑GB VRAM, Q5_K_M (file size 24.23 GB, memory 26.7 GB) or Q6_K (file size 28.01 GB, memory 30.5 GB).

What GPU do you need for MS3.2 PaintedFantasy Visage v3 34B?

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 (9.3 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q2_K_L (13.4 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (21.5 GB file, about 24.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K_L (28.3 GB file, about 30.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (36.3 GB file, about 38.8 GB in use).

Which MS3.2 PaintedFantasy Visage v3 34B quant should you choose?

Q4_K_M is the usual starting point for MS3.2 PaintedFantasy Visage v3 34B: it balances file size and quality well. Here it is a 20.7 GB file.

The Q8_0 file is 36.3 GB, about 1.8 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

Architecturellama
Parameters34B
Layers59
Trained context131,072 tokens
KV cache (fp16)236 KB per token

Source

Quantized bybartowski
Downloads (HF)1,789
Last updated2025-08-26

Frequently asked questions about MS3.2 PaintedFantasy Visage v3 34B

How much VRAM does MS3.2 PaintedFantasy Visage v3 34B need?

About 23.2 GB at Q4_K_M with an 8K context window. That is the 20.7 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 v3 34B 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 v3 34B GGUF?

It depends on the quant: file is 0.0 GB, IQ2_XXS is 9.3 GB, IQ2_XS is 10.3 GB, IQ2_S is 10.7 GB, IQ2_M is 11.6 GB, Q2_K is 12.7 GB and 22 more.

What context length does MS3.2 PaintedFantasy Visage v3 34B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.0 GB at 8K and 7.9 GB at 32K.

Where can I download MS3.2 PaintedFantasy Visage v3 34B GGUF?

The files are on Hugging Face in the bartowski/zerofata_MS3.2-PaintedFantasy-Visage-v3-34B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, using the IQ2_XXS quantization which requires approximately 11.8 GB of VRAM at 8K context.

Does the model support vision tasks?

No, the model has no vision capabilities.

What is the largest quantization available?

The largest quantization is Q8_0, with a file size of 36.27 GB and estimated memory 38.8 GB at 8K context.

Other GGUFs of MS3.2-PaintedFantasy-Visage-v3-34B

Similar models

Browse all →

More from bartowski

All by bartowski →

More Paintedfantasy models

All Paintedfantasy →

Other medium models

All medium models →