Tpn GGUF models

108 GGUF models in the Tpn family, quantized by 13 uploaders. Sizes run from 1.88B to 23.6B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
TP
tpn004 cand v3f aim
Tpn · tatjr13
Params23.6B
Context128K
Smallest14.7 GB
GGUF
TP
tpn004 cand v4f l1im
Tpn · tatjr13
Params23.6B
Context128K
Smallest18.3 GB
GGUF
TP
tpn004 cand v3f l1im
Tpn · tatjr13
Params23.6B
Context128K
Smallest18.3 GB
GGUF
TP
tpn004 cand v4f aim
Tpn · tatjr13
Params23.6B
Context128K
Smallest14.7 GB
GGUF
TP
tpn004 cand v1f aim
Tpn · tatjr13
Params23.6B
Context128K
Smallest14.7 GB
GGUF
TP
tpn005 e4
Tpn · tatjr13
Params8.49B
Context256K
Smallest7.2 GB
Tool use
TP
tpn005 v4
Tpn · tatjr13
Params8.49B
Context256K
Smallest7.2 GB
Tool use
TP
tpn005 r1pf
Tpn · tatjr13
Params8.49B
Context256K
Smallest7.2 GB
Tool use
TP
tpn 006 base
Tpn · tpnlabs
Params8.49B
Context256K
Smallest17.0 GB
Tool use
TP
tpn005 c2 union
Tpn · tatjr13
Params8.49B
Context256K
Smallest7.2 GB
Tool use
TP
tpn005 v7b
Tpn · tatjr13
Params8.49B
Context256K
Smallest7.2 GB
Tool use
TP
tpn005 c3 short
Tpn · tatjr13
Params8.49B
Context256K
Smallest7.2 GB
Tool use
TP
tpn 004 c11
Tpn · asura625
Params23.6B
Context128K
Smallest18.2 GB
Tool use
TP
tpn005 v3 d2
Tpn · tatjr13
Params8.49B
Context256K
Smallest7.2 GB
Tool use
TP
tpn005 r2 q5km
Tpn · tatjr13
Params8.49B
Context256K
Smallest6.3 GB
Tool use
TP
tpn005 c1 soup
Tpn · tatjr13
Params8.49B
Context256K
Smallest7.2 GB
Tool use
TP
tpn005 v5
Tpn · tatjr13
Params8.49B
Context256K
Smallest7.2 GB
Tool use
TP
tpn005 r1 q6k
Tpn · tatjr13
Params8.49B
Context256K
Smallest7.2 GB
ReasoningTool use
TP
tpn005 v6
Tpn · tatjr13
Params8.49B
Context256K
Smallest7.2 GB
Tool use
TP
tpn005 r0 q8
Tpn · tatjr13
Params8.49B
Context256K
Smallest9.0 GB
Tool use
TP
tpn005 rft
Tpn · tatjr13
Params8.49B
Context256K
Smallest7.2 GB
Tool use
TP
tpn005 d2 kvq8
Tpn · tatjr13
Params8.49B
Context256K
Smallest7.2 GB
Tool use
TP
tpn005 qc q3 k m
Tpn · tatjr13
Params23.6B
Context128K
Smallest11.5 GB
Tool use
TP
tpn005 e2d
Tpn · tatjr13
Params8.49B
Context256K
Smallest7.2 GB
Tool use
TP
tpn005 e2d b
Tpn · tatjr13
Params8.49B
Context256K
Smallest7.2 GB
Tool use
TP
tpn005 d1 calv3
Tpn · tatjr13
Params8.49B
Context256K
Smallest7.2 GB
Tool use
TP
tpn005 v7a
Tpn · tatjr13
Params8.49B
Context256K
Smallest7.2 GB
Tool use
TP
tpn005 k2
Tpn · asura625
Params8.49B
Context256K
Smallest7.2 GB
Tool use
TP
tpn005 e4 r2
Tpn · tatjr13
Params8.49B
Context256K
Smallest6.3 GB
Tool use
TP
tpn005 v7b d2
Tpn · tatjr13
Params8.49B
Context256K
Smallest7.2 GB
Tool use

About the Tpn GGUF models

Tpn is represented on ggufmodels.com by 108 GGUF models, quantized by 13 uploaders on Hugging Face. The most downloaded are tpn004 cand v3f aim, tpn004 cand v4f l1im and tpn004 cand v3f l1im. Parameter counts run from 1.88B to 23.6B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Tpn model is between 1.3 to 7.4 GB, which is the quant most people start with. Most files come from tatjr13 (50), asura625 (21) and ShinyUser (9). The quants you will meet most often are Q4_K_M (4), Q8_0 (3), Q5_K_S (3) and F16 (3), where the number is how many models offer that quant.

Frequently asked questions

Which Tpn GGUF should I download?

The most downloaded Tpn GGUF here is tpn004 cand v3f aim. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Tpn model need?

Q4_K_M files of Tpn models on this site range from 1.3 to 7.4 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Tpn GGUF files come from?

The most common quantizers here are tatjr13, asura625 and ShinyUser. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing