TR

Trinity

TrinityGGUF by arcee-aiUpdated 2026-05-28
Download on Hugging Face
Parameters399B
Context256K
Layers60
Architectureafmoe
Smallest quant81.2 GB
Quick answer

Trinity needs about 244.4 GB of memory at Q4_K_M (a 241.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 28 quants, from 81.2 GB (IQ1_S) to 423.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

Trinity-Large-Thinking: 398B sparse MoE model optimized for reasoning and tool use

Trinity-Large-Thinking is a 398B-parameter sparse Mixture-of-Experts model with ~13B active parameters per token. It is post‑trained with extended chain‑of‑thought reasoning and agentic RL. The model generates explicit reasoning traces wrapped in ` ... ` blocks before producing its final response.

Good at

  • Reasoning and chain‑of‑thought
  • Tool calling and agent workflows
  • Multi‑step planning

Limits

  • Requires large VRAM for high‑quant models
  • No vision support
  • License is OpenMDW‑1.1

Best for

  • Agentic applications
  • Complex problem solving
  • Tool‑enabled workflows

Who it’s for. Developers building agentic systems or requiring advanced reasoning in local deployments. The model is suitable for users who can allocate sufficient GPU memory and are comfortable with llama.cpp or LM Studio environments.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S81.2 GB (3 parts) 83.7 GB
Too big Get file →
IQ1_M90.9 GB (3 parts) 93.4 GB
Too big Get file →
IQ2_XXS106.0 GB (3 parts) 108.5 GB
Too big Get file →
IQ2_XS118.2 GB (3 parts) 120.8 GB
Too big Get file →
IQ2_S120.3 GB (4 parts) 122.8 GB
Too big Get file →
IQ2_M133.0 GB (4 parts) 135.5 GB
Too big Get file →
Q2_K139.2 GB (4 parts) 141.7 GB
Too big Get file →
Q2_K_L139.8 GB (4 parts) 142.3 GB
Too big Get file →
IQ3_XXS165.6 GB (5 parts) 168.1 GB
Too big Get file →
Q3_K_S173.0 GB (5 parts) 175.5 GB
Too big Get file →
IQ3_XS181.2 GB (5 parts) 183.7 GB
Too big Get file →
Q3_K_M181.4 GB (5 parts) 183.9 GB
Too big Get file →
Q3_K_L189.1 GB (5 parts) 191.6 GB
Too big Get file →
IQ3_M189.2 GB (5 parts) 191.8 GB
Too big Get file →
Q3_K_XL189.6 GB (5 parts) 192.1 GB
Too big Get file →
IQ4_XS213.0 GB (6 parts) 215.6 GB
Too big Get file →
IQ4_NL225.4 GB (6 parts) 227.9 GB
Too big Get file →
Q4_0226.3 GB (6 parts) 228.8 GB
Too big Get file →
Q4_K_S233.2 GB (6 parts) 235.7 GB
Too big Get file →
Q4_K_M241.8 GB (7 parts) 244.4 GB
Too big Get file →
Q4_K_L242.3 GB (7 parts) 244.8 GB
Too big Get file →
Q4_1250.1 GB (7 parts) 252.6 GB
Too big Get file →
Q5_K_S274.9 GB (8 parts) 277.4 GB
Too big Get file →
Q5_K_M283.6 GB (8 parts) 286.1 GB
Too big Get file →
Q5_K_L284.0 GB (8 parts) 286.5 GB
Too big Get file →
Q6_K343.2 GB (9 parts) 345.7 GB
Too big Get file →
Q6_K_L343.5 GB (9 parts) 346.0 GB
Too big Get file →
Q8_0423.7 GB (11 parts) 426.2 GB
Too big Get file →

For 8‑GB VRAM, use Q4_K_M (file size 241.85 GB, estimated memory 244.4 GB at 8k context). For 12‑GB VRAM, Q3_K_M (181.36 GB, 183.9 GB). For 16‑GB VRAM, Q2_K (139.22 GB, 141.7 GB). Estimates are approximate.

What GPU do you need for Trinity?

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 Trinity quant should you choose?

Q4_K_M is the usual starting point for Trinity: it balances file size and quality well. Here it is a 241.8 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 IQ1_S at 81.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 byarcee-ai
FamilyTrinity
Licenseother
Downloads (HF)598
Last updated2026-05-28

Frequently asked questions about Trinity

How much VRAM does Trinity need?

About 244.4 GB at Q4_K_M with an 8K context window. That is the 241.8 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 83.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Trinity GGUF?

It depends on the quant: IQ1_S is 81.2 GB, IQ1_M is 90.9 GB, IQ2_XXS is 106.0 GB, IQ2_XS is 118.2 GB, IQ2_S is 120.3 GB, IQ2_M is 133.0 GB and 22 more.

What context length does Trinity 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 GGUF?

The files are on Hugging Face in the arcee-ai/Trinity-Large-Thinking-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 use?

Hugging Face lists the license as other. 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 Q4_K_M on 8 GB VRAM?

No. Q4_K_M requires approximately 244.4 GB of memory at 8k context, far exceeding 8 GB VRAM.

Does Trinity support vision tasks?

No. The model has no vision capabilities.

What license applies to the GGUF weights?

The GGUF weights are released under the OpenMDW License, version 1.1.

Other GGUFs of Trinity-Large-Thinking

Similar models

Browse all →

More from arcee-ai

All by arcee-ai →

More Trinity models

All Trinity →

Other large models

All large models →