TP

tpn 003 sub a

TpnGGUF by 0xmsuUpdated 2026-09-05
Download on Hugging Face
Parameters11.9B
Context128K
Layers48
Architecturegemma4
Smallest quant7.4 GB
Quick answer

tpn 003 sub a needs about 20.8 GB of memory at its main file (a 7.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.

tpn 003 sub a is a 11.9B-parameter Tpn model in GGUF format, quantized by 0xmsu. Its trained context length is 128K tokens. The repository has 1 quant file, from 7.4 GB to 7.4 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—7.4 GB 20.8 GB
Too big Get file →

What GPU do you need for tpn 003 sub a?

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: the best quant that fits is the main file (7.4 GB file, about 20.8 GB in use).

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters11.9B
Layers48
Trained context131,072 tokens
KV cache (fp16)1536 KB per token

Source

Quantized by0xmsu
FamilyTpn
Downloads (HF)31
Last updated2026-09-05

Frequently asked questions about tpn 003 sub a

How much VRAM does tpn 003 sub a need?

About 20.8 GB at its main file with an 8K context window. That is the 7.4 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 tpn 003 sub a on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of tpn 003 sub a GGUF?

It depends on the quant: file is 7.4 GB.

What context length does tpn 003 sub a support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 12.9 GB at 8K and 51.5 GB at 32K.

Where can I download tpn 003 sub a GGUF?

The files are on Hugging Face in the 0xmsu/tpn-003-sub-a repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from 0xmsu

All by 0xmsu →

More Tpn models

All Tpn →

Other medium models

All medium models →