PR

Prosopon 31B

ProsoponGGUF by NimbzUpdated 2026-07-07
Download on Hugging Face
Parameters32.1B
Context256K
Layers60
Architecturegemma4
Smallest quant0.0 GB
Quick answer

Prosopon 31B needs about 52.2 GB of memory at Q4_K_M (a 19.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 23 quants, from 0.0 GB to 44.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

Prosopon 31B – a 32.1B‑parameter gemma4 model

Prosopon 31B is a 32.1B‑parameter gemma4 model trained on 262144 context tokens. It supports reasoning, roleplay, and tool use. The model is released under the apache-2.0 license.

Good at

  • reasoning
  • roleplay
  • tool integration

Limits

  • trained on 262144 tokens
  • no vision support
  • requires large VRAM for full precision

Best for

  • complex reasoning tasks
  • interactive storytelling
  • tool‑enabled workflows

Who it’s for. Developers and researchers needing a large, versatile language model for advanced reasoning and role‑playing scenarios. The model is suitable for applications that can accommodate its high memory footprint.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 32.7 GB
Too big Get file →
IQ2_M11.5 GB 44.2 GB
Too big Get file →
IQ3_XXS12.7 GB 45.4 GB
Too big Get file →
IQ3_S13.7 GB 46.4 GB
Too big Get file →
IQ3_M15.2 GB 47.9 GB
Too big Get file →
IQ4_XS17.5 GB 50.2 GB
Too big Get file →
Q4_018.5 GB 51.2 GB
Too big Get file →
Q4_K_S18.9 GB 51.6 GB
Too big Get file →
Q4_K_M19.5 GB 52.2 GB
Too big Get file →
Q4_K_M20.0 GB 52.8 GB
Too big Get file →
Q5_K_S22.3 GB 55.0 GB
Too big Get file →
Q5_K_S22.3 GB 55.0 GB
Too big Get file →
Q5_K_M22.8 GB 55.5 GB
Too big Get file →
Q5_K_M23.4 GB 56.1 GB
Too big Get file →
Q6_K26.4 GB 59.1 GB
Too big Get file →
Q6_K27.4 GB 60.2 GB
Too big Get file →
Q6_K29.7 GB 62.4 GB
Too big Get file →
Q6_K33.3 GB 66.0 GB
Too big Get file →
Q8_034.1 GB 66.8 GB
Too big Get file →
Q6_K34.6 GB 67.3 GB
Too big Get file →
Q8_036.8 GB 69.5 GB
Too big Get file →
Q6_K39.7 GB 72.4 GB
Too big Get file →
Q8_044.7 GB 77.4 GB
Too big Get file →

For 8 GB VRAM, use IQ2_M (11.52 GB, 44.2 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (19.48 GB, 52.2 GB memory) is a good balance. For 24 GB VRAM, Q5_K_M (22.81 GB, 55.5 GB memory) offers higher precision.

What GPU do you need for Prosopon 31B?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is IQ3_M (15.2 GB file, about 47.9 GB in use).

Which Prosopon 31B quant should you choose?

Q4_K_M is the usual starting point for Prosopon 31B: it balances file size and quality well. Here it is a 19.5 GB file.

The Q8_0 file is 34.1 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

Architecturegemma4
Parameters32.1B
Layers60
Trained context262,144 tokens
KV cache (fp16)3840 KB per token

Source

Quantized byNimbz
FamilyProsopon
Licenseapache-2.0
Downloads (HF)569
Last updated2026-07-07

Frequently asked questions about Prosopon 31B

How much VRAM does Prosopon 31B need?

About 52.2 GB at Q4_K_M with an 8K context window. That is the 19.5 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 Prosopon 31B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Prosopon 31B GGUF?

It depends on the quant: file is 0.0 GB, IQ2_M is 11.5 GB, IQ3_XXS is 12.7 GB, IQ3_S is 13.7 GB, IQ3_M is 15.2 GB, IQ4_XS is 17.5 GB and 17 more.

What context length does Prosopon 31B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 32.2 GB at 8K and 128.8 GB at 32K.

Where can I download Prosopon 31B GGUF?

The files are on Hugging Face in the Nimbz/Prosopon-31B-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 Prosopon 31B 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 Prosopon 31B on 8 GB VRAM?

Only the IQ2_M quant (11.52 GB file) is close, but it still requires about 44.2 GB memory at 8k context, so 8 GB VRAM is insufficient.

Does Prosopon 31B support vision?

No, the model has no vision capabilities.

What license applies to Prosopon 31B?

The model is released under the apache-2.0 license.

Other GGUFs of Prosopon-31B

Similar models

Browse all →

More from Nimbz

All by Nimbz →

More Prosopon models

All Prosopon →

Other medium models

All medium models →