Trinity GGUF models

83 GGUF models in the Trinity family, quantized by 28 uploaders. Sizes run from 6.1B to 399B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
TR
Models Arcee Ai Trinity Mini
Trinity · MaziyarPanahi
Params26B
Context128K
Q4_K_M15.8 GB
GGUF
TR
Trinity Nano Preview
Trinity · arcee-ai
Params6.12B
Context128K
Q4_K_M3.8 GB
GGUF
TR
Dolphin X1 Trinity Nano
Trinity · dphn
Params6.1B
Context128K
Smallest3.2 GB
GGUF
TR
Trinity Mini
Trinity · bartowski
Params26B
Context128K
Q4_K_M15.9 GB
GGUF
TR
Trinity Mini
Trinity · arcee-ai
Params26B
Context128K
Q4_K_M15.9 GB
GGUF
TR
Trinity Large Preview
Trinity · bartowski
Params399B
Context256K
Q4_K_M241.6 GB
GGUF
TR
Trinity-Large-Preview
Trinity · unsloth
Params399B
Context256K
Q4_K_M239.9 GB
Tool use
TR
Trinity Nano Preview
Trinity · bartowski
Params6.12B
Context128K
Q4_K_M3.8 GB
Tool use
TR
Trinity Mini Base Pre Anneal
Trinity · mradermacher
Params26B
Context4K
Q4_K_M15.8 GB
GGUF
TR
Trinity-Nano-Preview
Trinity · Mungert
Params6.12B
Context128K
Q4_K_M4.0 GB
Tool use
TR
Trinity Nano Base Pre Anneal
Trinity · mradermacher
Params6.12B
Context4K
Q4_K_M3.8 GB
GGUF
TR
Trinity
Trinity · bartowski
Params399B
Context256K
Q4_K_M241.8 GB
ReasoningTool use
TR
Trinity Mini
Trinity · mradermacher
Params26.1B
Context128K
Q4_K_M15.8 GB
ReasoningTool use
TR
Trinity Large TrueBase i1
Trinity · mradermacher
Params399B
Context8K
Smallest0.5 GB
GGUF
TR
Trinity Mini Lora 2
Trinity · mradermacher
Params26.1B
Context128K
Q4_K_M15.8 GB
ReasoningTool use
TR
Trinity Nano Base
Trinity · mradermacher
Params6.12B
Context128K
Q4_K_M3.8 GB
Tool use
TR
Trinity Nano Preview
Trinity · mradermacher
Params6.12B
Context128K
Q4_K_M3.8 GB
Tool use
TR
Trinity Large Base
Trinity · bartowski
Params399B
Context256K
Q4_K_M241.6 GB
GGUF
TR
Trinity Large TrueBase
Trinity · bartowski
Params399B
Context8K
Q4_K_M241.6 GB
GGUF
TR
Trinity Mini Base
Trinity · mradermacher
Params26.1B
Context128K
Q4_K_M15.8 GB
Tool use
TR
Trinity
Trinity · arcee-ai
Params399B
Context256K
Q4_K_M241.8 GB
ReasoningTool use
TR
Trinity Large Preview
Trinity · arcee-ai
Params390B
Context—
Q4_K_M241.6 GB
GGUF
TR
Trinity_Notus2-xb
Trinity · mradermacher
Params11.2B
Context32K
Q4_K_M6.7 GB
GGUF
TR
Trinity Mini
Trinity · mradermacher
Params26.1B
Context128K
Q4_K_M15.8 GB
ReasoningTool use
TR
Arcee ai.Trinity Large Preview
Trinity · DevQuasar
Params399B
Context256K
Q4_K_M239.6 GB
Tool use
TR
Trinity Mini Quirky
Trinity · mradermacher
Params26.1B
Context128K
Q4_K_M15.8 GB
ReasoningTool use
TR
Trinity Mini Quirky
Trinity · mradermacher
Params26.1B
Context128K
Q4_K_M15.8 GB
ReasoningTool use
TR
Trinity Nano Base Pre Anneal
Trinity · mradermacher
Params6.12B
Context4K
Q4_K_M3.8 GB
GGUF
TR
Trinity Mini Base Pre Anneal
Trinity · mradermacher
Params26.1B
Context4K
Q4_K_M15.8 GB
GGUF
TR
Trinity Nano Base
Trinity · mradermacher
Params6.12B
Context128K
Q4_K_M3.8 GB
Tool use

About the Trinity GGUF models

Trinity is represented on ggufmodels.com by 83 GGUF models, quantized by 28 uploaders on Hugging Face. The most downloaded are Models Arcee Ai Trinity Mini, Trinity Nano Preview and Dolphin X1 Trinity Nano. Parameter counts run from 6.1B to 399B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Trinity model is between 3.8 to 241.8 GB, which is the quant most people start with. Most files come from mradermacher (29), lyraaaa (10) and bartowski (6). The quants you will meet most often are Q4_K_M (58), Q5_K_M (51), Q8_0 (50) and Q3_K_M (49), where the number is how many models offer that quant.

Frequently asked questions

Which Trinity GGUF should I download?

The most downloaded Trinity GGUF here is Models Arcee Ai Trinity Mini. 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 Trinity model need?

Q4_K_M files of Trinity models on this site range from 3.8 to 241.8 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 Trinity GGUF files come from?

The most common quantizers here are mradermacher, lyraaaa and bartowski. 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