TR

Trinity Large Base

TrinityGGUF by bartowskiUpdated 2026-02-01
Download on Hugging Face
Parameters399B
Context256K
Layers60
Architectureafmoe
Smallest quant0.5 GB
Quick answer

Trinity Large Base needs about 244.1 GB of memory at Q4_K_M (a 241.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 27 quants, from 0.5 GB to 423.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

Trinity Large Base – 399B‑parameter sparse MoE foundation model

Trinity Large Base is a 399‑billion‑parameter sparse Mixture‑of‑Experts model with 13B active parameters per token. It was pretrained on 17 trillion tokens and released under the Apache‑2.0 license. The model supports 262,144‑token context.

Good at

  • Large‑scale language modeling
  • Sparse MoE efficiency
  • High‑capacity foundation

Limits

  • No instruction tuning or RLHF
  • Large VRAM requirement for full precision
  • No vision support

Best for

  • Research on sparse MoE architectures
  • Fine‑tuning downstream tasks
  • Benchmarking large‑scale LLMs

Who it’s for. Researchers and developers needing a high‑capacity foundation model for experimentation and fine‑tuning. The model is suitable for those who can allocate sufficient GPU memory and are comfortable working with sparse MoE checkpoints.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.5 GB 3.0 GB
Fits Get file →
IQ1_S81.7 GB (3 parts) 84.2 GB
Too big Get file →
IQ1_M85.1 GB (3 parts) 87.6 GB
Too big Get file →
IQ2_XXS95.1 GB (3 parts) 97.6 GB
Too big Get file →
IQ2_XS109.8 GB (3 parts) 112.3 GB
Too big Get file →
IQ2_S110.1 GB (3 parts) 112.6 GB
Too big Get file →
IQ2_M125.1 GB (4 parts) 127.6 GB
Too big Get file →
Q2_K139.0 GB (4 parts) 141.5 GB
Too big Get file →
Q2_K_L139.6 GB (4 parts) 142.1 GB
Too big Get file →
IQ3_XXS157.0 GB (4 parts) 159.5 GB
Too big Get file →
IQ3_XS162.4 GB (5 parts) 164.9 GB
Too big Get file →
Q3_K_S172.8 GB (5 parts) 175.3 GB
Too big Get file →
IQ3_M181.0 GB (5 parts) 183.6 GB
Too big Get file →
Q3_K_M181.2 GB (5 parts) 183.7 GB
Too big Get file →
Q3_K_L188.8 GB (5 parts) 191.3 GB
Too big Get file →
Q3_K_XL189.3 GB (5 parts) 191.8 GB
Too big Get file →
IQ4_XS212.8 GB (6 parts) 215.3 GB
Too big Get file →
IQ4_NL225.2 GB (6 parts) 227.7 GB
Too big Get file →
Q4_0229.0 GB (6 parts) 231.6 GB
Too big Get file →
Q4_K_S233.1 GB (6 parts) 235.6 GB
Too big Get file →
Q4_K_M241.6 GB (7 parts) 244.1 GB
Too big Get file →
Q4_K_L242.1 GB (7 parts) 244.6 GB
Too big Get file →
Q4_1249.9 GB (7 parts) 252.4 GB
Too big Get file →
Q5_K_S274.7 GB (8 parts) 277.3 GB
Too big Get file →
Q5_K_M283.3 GB (8 parts) 285.8 GB
Too big Get file →
Q6_K327.6 GB (9 parts) 330.1 GB
Too big Get file →
Q8_0423.7 GB (11 parts) 426.2 GB
Too big Get file →

For 8 GB VRAM, the smallest quant is IQ1_S at 81.67 GB, which still exceeds the memory budget. A more realistic option is Q4_K_M (241.63 GB, 244.1 GB at 8 k context) for systems with 16 GB VRAM. For 32 GB VRAM, Q5_K_M (283.32 GB, 285.8 GB) is recommended. Estimates are approximate.

What GPU do you need for Trinity Large 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: the best quant that fits is the main file (0.5 GB file, about 3.0 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.0 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.0 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.0 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.0 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.0 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.0 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.0 GB in use).

Which Trinity Large Base quant should you choose?

Q4_K_M is the usual starting point for Trinity Large Base: it balances file size and quality well. Here it is a 241.6 GB file.

The Q8_0 file is 423.7 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is the first one in the table at 0.5 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureafmoe
Parameters399B (approximate, mixture of experts)
Layers60
Trained context262,144 tokens
KV cache (fp16)240 KB per token

Source

Quantized bybartowski
FamilyTrinity
Licenseapache-2.0
Downloads (HF)700
Last updated2026-02-01

Frequently asked questions about Trinity Large Base

How much VRAM does Trinity Large Base need?

About 244.1 GB at Q4_K_M with an 8K context window. That is the 241.6 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 Trinity Large Base on an 8 GB GPU?

Yes, with the smaller files: the 0.5 GB file needs about 3.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Trinity Large Base GGUF?

It depends on the quant: file is 0.5 GB, IQ1_S is 81.7 GB, IQ1_M is 85.1 GB, IQ2_XXS is 95.1 GB, IQ2_XS is 109.8 GB, IQ2_S is 110.1 GB and 21 more.

What context length does Trinity Large Base support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download Trinity Large Base GGUF?

The files are on Hugging Face in the bartowski/arcee-ai_Trinity-Large-Base-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Trinity Large Base use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Trinity Large Base on 8 GB VRAM?

No. The smallest quant file is 81.67 GB, which far exceeds 8 GB VRAM. You would need a GPU with at least 16 GB VRAM for the Q4_K_M quant.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Does this model support vision tasks?

No. The model has no vision capabilities.

Other GGUFs of Trinity-Large-Base

Similar models

Browse all →

More from bartowski

All by bartowski →

More Trinity models

All Trinity →

Other large models

All large models →