TP

tpn 004 base

TpnGGUF by tpnlabsUpdated 2026-09-10
Download on Hugging Face
Parameters23.6B
Context128K
Layers40
Architecturemistral3
Smallest quant47.2 GB
Quick answer

tpn 004 base needs about 49.0 GB of memory at BF16 (a 47.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

tpn 004 base is a 23.6B-parameter Tpn model in GGUF format, quantized by tpnlabs. Its trained context length is 128K tokens. The repository has 1 quant file, from 47.2 GB (BF16) to 47.2 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF1647.2 GB 49.0 GB
Too big Get file →

What GPU do you need for tpn 004 base?

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: no quant fits at an 8K context.

Which tpn 004 base quant should you choose?

BF16 (47.2 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

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

Source

Quantized bytpnlabs
FamilyTpn
Downloads (HF)17
Last updated2026-09-10

Frequently asked questions about tpn 004 base

How much VRAM does tpn 004 base need?

About 49.0 GB at BF16 with an 8K context window. That is the 47.2 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 base on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 49.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of tpn 004 base GGUF?

It depends on the quant: BF16 is 47.2 GB.

What context length does tpn 004 base 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 base GGUF?

The files are on Hugging Face in the tpnlabs/tpn-004-base 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 tpnlabs

All by tpnlabs →

More Tpn models

All Tpn →

Other medium models

All medium models →