TP

tpn 004 c7

TpnGGUF by asura625Updated 2026-09-13
Download on Hugging Face
Parameters23.6B
Context128K
Layers40
Architecturemistral3
Smallest quant18.2 GB
Quick answer

tpn 004 c7 needs about 20.1 GB of memory at its main file (a 18.2 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 5.4 GB.

tpn 004 c7 is a 23.6B-parameter Tpn model in GGUF format, quantized by asura625. Its trained context length is 128K tokens. The repository has 1 quant file, from 18.2 GB to 18.2 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—18.2 GB 20.1 GB
Too big Get file →

What GPU do you need for tpn 004 c7?

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 (18.2 GB file, about 20.1 GB in use).

Specifications

Architecture from the GGUF header

Architecturemistral3
Parameters23.6B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized byasura625
FamilyTpn
Downloads (HF)65
Last updated2026-09-13

Frequently asked questions about tpn 004 c7

How much VRAM does tpn 004 c7 need?

About 20.1 GB at its main file with an 8K context window. That is the 18.2 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 004 c7 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of tpn 004 c7 GGUF?

It depends on the quant: file is 18.2 GB.

What context length does tpn 004 c7 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download tpn 004 c7 GGUF?

The files are on Hugging Face in the asura625/tpn-004-c7 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 asura625

All by asura625 →

More Tpn models

All Tpn →

Other medium models

All medium models →