TR

Trinity Nano Preview

TrinityGGUF by mradermacherUpdated 2026-06-23
Download on Hugging Face
Parameters6.12B
Context128K
Layers56
Architectureafmoe
Smallest quant0.1 GB
Quick answer

Trinity Nano Preview needs about 4.7 GB of memory at Q4_K_M (a 3.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.1 GB to 5.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Trinity Nano Preview – a 6B MoE chat model with 1B active parameters

Trinity Nano Preview is a 6B parameter model with 1B active parameters. It uses an AfmoeForCausalLM architecture and supports a 128k context length. The model is chat‑tuned and includes tools capability.

Good at

  • Chatting with a charming personality
  • Tool usage
  • Handling 128k context

Limits

  • May be unstable due to high sparsity
  • Experimental release, not hosted
  • Requires 8k context for memory estimates

Best for

  • Small‑scale enterprise chatbots
  • Tinkerers exploring MoE models
  • Testing 128k context applications

Who it’s for. Developers and researchers interested in experimenting with a small, sparse Mixture‑of‑Experts model. It is suitable for those who can run the model locally and are comfortable with experimental releases.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 1.0 GB
Fits Get file →
IQ1_S1.4 GB 2.4 GB
Fits Get file →
IQ1_M1.5 GB 2.5 GB
Fits Get file →
IQ2_XXS1.7 GB 2.7 GB
Fits Get file →
IQ2_XS1.9 GB 2.9 GB
Fits Get file →
IQ2_S1.9 GB 2.9 GB
Fits Get file →
IQ2_M2.1 GB 3.1 GB
Fits Get file →
Q2_K_S2.2 GB 3.2 GB
Fits Get file →
Q2_K2.3 GB 3.3 GB
Fits Get file →
IQ3_XXS2.4 GB 3.4 GB
Fits Get file →
IQ3_XS2.6 GB 3.6 GB
Fits Get file →
Q3_K_S2.7 GB 3.7 GB
Fits Get file →
IQ3_S2.7 GB 3.7 GB
Fits Get file →
IQ3_M2.8 GB 3.7 GB
Fits Get file →
Q3_K_M3.0 GB 4.0 GB
Fits Get file →
Q3_K_L3.2 GB 4.2 GB
Fits Get file →
IQ4_XS3.3 GB 4.3 GB
Fits Get file →
IQ4_NL3.5 GB 4.5 GB
Fits Get file →
Q4_03.5 GB 4.5 GB
Fits Get file →
Q4_K_S3.5 GB 4.5 GB
Fits Get file →
Q4_K_M3.8 GB 4.7 GB
Fits Get file →
Q4_13.9 GB 4.9 GB
Fits Get file →
Q5_K_S4.3 GB 5.2 GB
Fits Get file →
Q5_K_M4.4 GB 5.4 GB
Fits Get file →
Q6_K5.1 GB 6.0 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 3.76 GB, estimated 4.7 GB memory). For 16 GB VRAM, Q5_K_M (4.38 GB, 5.4 GB memory) or Q6_K (5.05 GB, 6 GB memory). For 4 GB VRAM, IQ1_S (1.38 GB, 2.4 GB memory) is the smallest viable quant.

What GPU do you need for Trinity Nano Preview?

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 Q3_K_M (3.0 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (5.1 GB file, about 6.0 GB in use).

Which Trinity Nano Preview quant should you choose?

Q4_K_M is the usual starting point for Trinity Nano Preview: it balances file size and quality well. Here it is a 3.8 GB file.

If memory is tight, the smallest file is the first one in the table at 0.1 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
Parameters6.12B (approximate, mixture of experts)
Layers56
Trained context131,072 tokens
KV cache (fp16)56 KB per token

Source

Quantized bymradermacher
FamilyTrinity
Licenseother
Downloads (HF)706
Last updated2026-06-23

Frequently asked questions about Trinity Nano Preview

How much VRAM does Trinity Nano Preview need?

About 4.7 GB at Q4_K_M with an 8K context window. That is the 3.8 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 Nano Preview on an 8 GB GPU?

Yes, with Q6_K: the 5.1 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Trinity Nano Preview GGUF?

It depends on the quant: file is 0.1 GB, IQ1_S is 1.4 GB, IQ1_M is 1.5 GB, IQ2_XXS is 1.7 GB, IQ2_XS is 1.9 GB, IQ2_S is 1.9 GB and 19 more.

What context length does Trinity Nano Preview support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download Trinity Nano Preview GGUF?

The files are on Hugging Face in the mradermacher/Trinity-Nano-Preview-i1-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 Nano Preview 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 Trinity Nano Preview on 8 GB VRAM?

Yes, the Q4_K_M quant requires approximately 4.7 GB memory at 8k context, which fits within 8 GB VRAM.

Does this model support vision?

No, the model has no vision capability.

Is the model stable for production use?

It is experimental and may be unstable in certain use cases due to high sparsity.

Other GGUFs of Trinity-Nano-Preview

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Trinity models

All Trinity →

Other small models

All small models →