Models

Trinity Large Preview

Arcee · January 2026

Get

Hugging Face

A 399B, 13B active chat model from Arcee.

Rating: 3.8
Downloads: 1.3K
Likes: 13
Parameters: 399B, 13B active
Context: 256K
Licence: other

Too big for this Mac

Its smallest size needs 182 GB of memory, more than M4 · 16 GB can give it.

Ratings

3.8 out of 5, across people's blind votes on its answers.

Text: 1379
Coding: 1443

LM Arena ratings of October 28, 2026 (CC BY 4.0): people vote between two answers without knowing which model wrote which. The bar ends at 1488, the best any open model has. The Arena tests the full model; a small size on a Mac answers a little worse.

Trinity Large Preview runs well from a Mac with an M2 Ultra and 192 GB of memory. 5 of 59 Mac configurations run it well.

Compare with

The nearest models in size.

Sizes

From unsloth/Trinity-Large-Preview-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

Size	Download	Memory at 8K	Get
Q2_K	145 GB	146 GBestimated	Open
Q2_K_L	145 GB	146 GBestimated	Open
UD-Q2_K_XL	146 GB	147 GBestimated	Open
UD-IQ2_XXS	153 GB	155 GBestimated	Open
UD-IQ2_M	154 GB	156 GBestimated	Open
Q3_K_S	172 GB	173 GBestimated	Open
UD-IQ3_XXS	183 GB	184 GBestimated	Open
Q3_K_M	189 GB	191 GBestimated	Open
UD-Q3_K_XL	190 GB	191 GBestimated	Open
IQ4_XS	212 GB	214 GBestimated	Open
IQ4_NL	225 GB	226 GBestimated	Open
Q4_0	225 GB	226 GBestimated	Open
Q4_K_S	225 GB	226 GBestimated	Open
Q4_K_M	240 GB	241 GBestimated	Open
UD-Q4_K_XL	247 GB	249 GBestimated	Open
Q4_1	250 GB	251 GBestimated	Open
Q5_K_S	274 GB	276 GBestimated	Open
Q5_K_M	282 GB	284 GBestimated	Open
UD-Q5_K_XL	285 GB	286 GBestimated	Open
Q6_K	327 GB	329 GBestimated	Open
UD-Q6_K_XL	342 GB	343 GBestimated	Open
Q8_0	424 GB	425 GBestimated	Open
UD-Q8_K_XL	467 GB	469 GBestimated	Open
BF16	797 GB	799 GBestimated	Open

Run It Anywhere

Trinity Large Preview is an open model, so any app that runs GGUF files can run it. These take the Q2_K size from unsloth straight from Hugging Face.

LM StudioMac, Windows, LinuxOpen
JanMac, Windows, LinuxOpen
MstyMac, Windows, LinuxOpen
OllamaMac, Windows, Linuxollama run hf.co/unsloth/Trinity-Large-Preview-GGUF:Q2_K
llama.cppMac, Windows, Linuxllama-server -hf unsloth/Trinity-Large-Preview-GGUF:Q2_K
Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/unsloth/Trinity-Large-Preview-GGUF:Q2_K

On a PC Graphics Card

Video memory	Largest size that fits	Memory at 8K
6 GB	None worth running	needs 147 GB
8 GB	None worth running	needs 147 GB
10 GB	None worth running	needs 147 GB
11 GB	None worth running	needs 147 GB
12 GB	None worth running	needs 147 GB
16 GB	None worth running	needs 147 GB
20 GB	None worth running	needs 147 GB
24 GB	None worth running	needs 147 GB
32 GB	None worth running	needs 147 GB
48 GB	None worth running	needs 147 GB

The largest size, of those that keep three bits a weight or more, whose memory at an 8K chat is under 92% of the card's; the rest is the desktop's. Estimated from the files, the same way as for a Mac; speed on a PC is not estimated yet. A size that doesn't fit the card still runs, slower, with part of it in ordinary memory.

On every Mac

Mac	Size	Fit	Memory	Writes
M6 · 16 GB	Q2_K	Too big	182 GB
M6 · 24 GB	Q2_K	Too big	182 GB
M6 · 32 GB	Q2_K	Too big	182 GB
M5 · 16 GB	Q2_K	Too big	182 GB
M5 · 24 GB	Q2_K	Too big	182 GB
M5 · 32 GB	Q2_K	Too big	182 GB
M5 Pro · 24 GB	Q2_K	Too big	182 GB
M5 Pro · 48 GB	Q2_K	Too big	182 GB
M5 Pro · 64 GB	Q2_K	Too big	182 GB
M5 Max · 36 GB	Q2_K	Too big	182 GB
M5 Max · 48 GB	Q2_K	Too big	182 GB
M5 Max · 64 GB	Q2_K	Too big	182 GB
M5 Max · 128 GB	Q2_K	Too big	182 GB
M5 Ultra · 96 GB	Q2_K	Too big	182 GB
M5 Ultra · 256 GB	Q3_K_S	Runs great	174 GB	31
M5 Ultra · 512 GB	UD-Q6_K_XL	Runs great	347 GB	23
M4 · 16 GB	Q2_K	Too big	182 GB
M4 · 24 GB	Q2_K	Too big	182 GB
M4 · 32 GB	Q2_K	Too big	182 GB
M4 Pro · 24 GB	Q2_K	Too big	182 GB
M4 Pro · 48 GB	Q2_K	Too big	182 GB
M4 Pro · 64 GB	Q2_K	Too big	182 GB
M4 Max · 36 GB	Q2_K	Too big	182 GB
M4 Max · 48 GB	Q2_K	Too big	182 GB
M4 Max · 64 GB	Q2_K	Too big	182 GB
M4 Max · 96 GB	Q2_K	Too big	182 GB
M4 Max · 128 GB	Q2_K	Too big	182 GB
M3 · 8 GB	Q2_K	Too big	182 GB
M3 · 16 GB	Q2_K	Too big	182 GB
M3 · 24 GB	Q2_K	Too big	182 GB
M3 Pro · 18 GB	Q2_K	Too big	182 GB
M3 Pro · 36 GB	Q2_K	Too big	182 GB
M3 Max · 36 GB	Q2_K	Too big	182 GB
M3 Max · 48 GB	Q2_K	Too big	182 GB
M3 Max · 64 GB	Q2_K	Too big	182 GB
M3 Max · 96 GB	Q2_K	Too big	182 GB
M3 Max · 128 GB	Q2_K	Too big	182 GB
M3 Ultra · 96 GB	Q2_K	Too big	182 GB
M3 Ultra · 256 GB	Q3_K_S	Runs great	174 GB	17
M3 Ultra · 512 GB	UD-Q6_K_XL	Runs great	347 GB	13
M2 · 8 GB	Q2_K	Too big	182 GB
M2 · 16 GB	Q2_K	Too big	182 GB
M2 · 24 GB	Q2_K	Too big	182 GB
M2 Pro · 16 GB	Q2_K	Too big	182 GB
M2 Pro · 32 GB	Q2_K	Too big	182 GB
M2 Max · 32 GB	Q2_K	Too big	182 GB
M2 Max · 64 GB	Q2_K	Too big	182 GB
M2 Max · 96 GB	Q2_K	Too big	182 GB
M2 Ultra · 64 GB	Q2_K	Too big	182 GB
M2 Ultra · 128 GB	Q2_K	Too big	182 GB
M2 Ultra · 192 GB	UD-Q2_K_XL	Runs well	151 GB	18
M1 · 8 GB	Q2_K	Too big	182 GB
M1 · 16 GB	Q2_K	Too big	182 GB
M1 Pro · 16 GB	Q2_K	Too big	182 GB
M1 Pro · 32 GB	Q2_K	Too big	182 GB
M1 Max · 32 GB	Q2_K	Too big	182 GB
M1 Max · 64 GB	Q2_K	Too big	182 GB
M1 Ultra · 64 GB	Q2_K	Too big	182 GB
M1 Ultra · 128 GB	Q2_K	Too big	182 GB

Writes is words a second, estimated from the Mac's memory speed and the model's size; how, and how wrong.

Information

Maker: Arcee
Released: January 2026
Parameters: 399B, 13B active
Longest chat: 256K tokens
Reads pictures: No
Licence: other
Downloads this month: 1,311
Likes: 13
Sizes: 24, 145 to 797 GB
Kind: Maker's release
Source: arcee-ai/Trinity-Large-Preview

Badge for the model card

Shows on Trinity Large Preview's Hugging Face card which Macs run it well, linked to this page. It updates every morning.

Files, downloads and likes read from Hugging Face on November 5, 2026 and refreshed every morning. Memory and speed are estimates until someone running Outmake measures this model on that Mac.