TR

Trinity Nano Base Pre Anneal

TrinityGGUF by mradermacherUpdated 2026-06-03
Download on Hugging Face
Parameters6.12B
Context4K
Layers56
Architectureafmoe
Smallest quant0.1 GB
Quick answer

Trinity Nano Base Pre Anneal 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).

6B MoE model with 1B active parameters

Trinity Nano Base Pre Anneal is a 6B parameter AfmoeForCausalLM model with 1B active parameters. It is trained on 8.8T tokens and supports a 4K context length. The model is intended for domain‑specific fine‑tuning rather than general chat.

Good at

  • Math and code reasoning
  • Domain‑specific fine‑tuning
  • Efficient inference with MoE

Limits

  • 4K context length only
  • Not suitable for general chat without finetuning
  • No vision support

Best for

  • Fine‑tuning for enterprise use
  • Embedding generation for niche domains
  • Low‑latency inference on modest GPUs

Who it’s for. Engineers and researchers who need a lightweight MoE model for specialized tasks. The model requires further fine‑tuning before it can be used for general conversational AI.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 0.8 GB
Fits Get file →
IQ1_S1.4 GB 2.1 GB
Fits Get file →
IQ1_M1.5 GB 2.2 GB
Fits Get file →
IQ2_XXS1.7 GB 2.5 GB
Fits Get file →
IQ2_XS1.9 GB 2.6 GB
Fits Get file →
IQ2_S1.9 GB 2.7 GB
Fits Get file →
IQ2_M2.1 GB 2.8 GB
Fits Get file →
Q2_K_S2.2 GB 2.9 GB
Fits Get file →
Q2_K2.3 GB 3.1 GB
Fits Get file →
IQ3_XXS2.4 GB 3.2 GB
Fits Get file →
IQ3_XS2.6 GB 3.3 GB
Fits Get file →
Q3_K_S2.7 GB 3.5 GB
Fits Get file →
IQ3_S2.7 GB 3.5 GB
Fits Get file →
IQ3_M2.8 GB 3.5 GB
Fits Get file →
Q3_K_M3.0 GB 3.7 GB
Fits Get file →
Q3_K_L3.2 GB 4.0 GB
Fits Get file →
IQ4_XS3.3 GB 4.1 GB
Fits Get file →
IQ4_NL3.5 GB 4.3 GB
Fits Get file →
Q4_03.5 GB 4.3 GB
Fits Get file →
Q4_K_S3.5 GB 4.3 GB
Fits Get file →
Q4_K_M3.8 GB 4.5 GB
Fits Get file →
Q4_13.9 GB 4.6 GB
Fits Get file →
Q5_K_S4.3 GB 5.0 GB
Fits Get file →
Q5_K_M4.4 GB 5.1 GB
Fits Get file →
Q6_K5.1 GB 5.8 GB
Fits Get file →

For 8GB VRAM use IQ1_S (2.4 GB) or IQ1_M (2.5 GB). For 12GB VRAM use Q2_K (3.3 GB) or Q3_K_M (4 GB). For 16GB VRAM use Q4_K_M (4.7 GB) or Q5_K_M (5.4 GB). Estimates are approximate.

What GPU do you need for Trinity Nano Base Pre Anneal?

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 Base Pre Anneal quant should you choose?

Q4_K_M is the usual starting point for Trinity Nano Base Pre Anneal: 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 context4,096 tokens
KV cache (fp16)56 KB per token

Source

Quantized bymradermacher
FamilyTrinity
Licenseother
Downloads (HF)998
Last updated2026-06-03

Frequently asked questions about Trinity Nano Base Pre Anneal

How much VRAM does Trinity Nano Base Pre Anneal 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 Base Pre Anneal 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 Base Pre Anneal 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 Base Pre Anneal support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.2 GB at 4K.

Where can I download Trinity Nano Base Pre Anneal GGUF?

The files are on Hugging Face in the mradermacher/Trinity-Nano-Base-Pre-Anneal-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 Base Pre Anneal 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 this model on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quant, which use about 2.4–2.5 GB of VRAM at 8K context.

Does this model support vision?

No, the model has no vision capabilities.

Is it ready for general chat?

No, it requires domain‑specific fine‑tuning before it can be used for general chat.

Other GGUFs of Trinity-Nano-Base-Pre-Anneal

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Trinity models

All Trinity →

Other small models

All small models →