TR

Trinity Mini

TrinityGGUF by bartowskiUpdated 2025-12-01
Download on Hugging Face
Parameters26B
Context128K
Layers32
Architectureafmoe
Smallest quant0.1 GB
Quick answer

Trinity Mini needs about 17.0 GB of memory at Q4_K_M (a 15.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 28 quants, from 0.1 GB to 52.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.

Trinity Mini – 26B MoE model with 3B active parameters

Trinity Mini is a 26B parameter AfmoeForCausalLM model with 3B active parameters. It supports a 128k context length and is tuned for reasoning. The model is released under the Apache‑2.0 license.

Good at

  • Reasoning tasks
  • Instruction following
  • Long‑form generation

Limits

  • Large VRAM required for high‑quality quants
  • No vision support
  • Requires 128k context for full capability

Best for

  • Enterprise chatbots
  • Code generation
  • Data analysis

Who it’s for. Developers and enterprises needing a medium‑sized MoE model for reasoning and instruction tasks. Suitable for users with access to GPUs that can handle the memory demands of the larger quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 1.1 GB
Fits Get file →
IQ2_XXS6.6 GB 7.6 GB
Tight Get file →
IQ2_XS7.5 GB 8.5 GB
Too big Get file →
IQ2_S7.6 GB 8.6 GB
Too big Get file →
IQ2_M8.5 GB 9.5 GB
Too big Get file →
Q2_K9.4 GB 10.5 GB
Too big Get file →
Q2_K_L9.8 GB 10.9 GB
Too big Get file →
IQ3_XXS10.5 GB 11.6 GB
Too big Get file →
IQ3_XS11.0 GB 12.0 GB
Too big Get file →
Q3_K_S11.6 GB 12.6 GB
Too big Get file →
IQ3_M12.1 GB 13.1 GB
Too big Get file →
Q3_K_M12.1 GB 13.1 GB
Too big Get file →
Q3_K_L12.5 GB 13.5 GB
Too big Get file →
Q3_K_XL12.9 GB 13.9 GB
Too big Get file →
IQ4_XS14.2 GB 15.2 GB
Too big Get file →
IQ4_NL14.9 GB 16.0 GB
Too big Get file →
Q4_015.1 GB 16.2 GB
Too big Get file →
Q4_K_S15.4 GB 16.5 GB
Too big Get file →
Q4_K_M15.9 GB 17.0 GB
Too big Get file →
Q4_K_L16.2 GB 17.3 GB
Too big Get file →
Q4_116.5 GB 17.5 GB
Too big Get file →
Q5_K_S18.1 GB 19.1 GB
Too big Get file →
Q5_K_M18.6 GB 19.7 GB
Too big Get file →
Q5_K_L18.9 GB 19.9 GB
Too big Get file →
Q6_K21.5 GB 22.6 GB
Too big Get file →
Q6_K_L21.7 GB 22.8 GB
Too big Get file →
Q8_027.8 GB 28.8 GB
Too big Get file →
BF1652.3 GB (2 parts) 53.3 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (0.08 GB file, 1.1 GB memory) or IQ2_XS (7.48 GB file, 8.5 GB memory). For 16 GB VRAM, Q4_K_M (15.94 GB file, 17 GB memory) or Q5_K_M (18.64 GB file, 19.7 GB memory) are suitable. For 32 GB VRAM, Q6_K (21.52 GB file, 22.6 GB memory) or Q8_0 (27.79 GB file, 28.8 GB memory) provide higher quality.

What GPU do you need for Trinity Mini?

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 (0.1 GB file, about 1.1 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.1 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ2_XXS (6.6 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ3_XS (11.0 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ4_NL (14.9 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K_L (21.7 GB file, about 22.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (27.8 GB file, about 28.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (27.8 GB file, about 28.8 GB in use).

Which Trinity Mini quant should you choose?

Q4_K_M is the usual starting point for Trinity Mini: it balances file size and quality well. Here it is a 15.9 GB file.

The Q8_0 file is 27.8 GB, about 1.7 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 0.1 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
Parameters26B (approximate, mixture of experts)
Layers32
Trained context131,072 tokens
KV cache (fp16)64 KB per token

Source

Quantized bybartowski
FamilyTrinity
Licenseapache-2.0
Downloads (HF)1,911
Last updated2025-12-01

Frequently asked questions about Trinity Mini

How much VRAM does Trinity Mini need?

About 17.0 GB at Q4_K_M with an 8K context window. That is the 15.9 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 Mini on an 8 GB GPU?

Yes, with IQ2_XXS: the 6.6 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Trinity Mini GGUF?

It depends on the quant: file is 0.1 GB, IQ2_XXS is 6.6 GB, IQ2_XS is 7.5 GB, IQ2_S is 7.6 GB, IQ2_M is 8.5 GB, Q2_K is 9.4 GB and 22 more.

What context length does Trinity Mini 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 2.1 GB at 32K.

Where can I download Trinity Mini GGUF?

The files are on Hugging Face in the bartowski/arcee-ai_Trinity-Mini-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 Mini 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 Mini on 8 GB VRAM?

Yes, using the IQ2_XXS or IQ2_XS quantizations which require approximately 1.1 or 8.5 GB of VRAM at 8k context.

Does Trinity Mini support vision tasks?

No, the model has no vision capabilities.

What is the recommended context length for best performance?

The model is designed for a 128k context length to fully utilize its reasoning abilities.

Other GGUFs of Trinity-Mini

Similar models

Browse all →

More from bartowski

All by bartowski →

More Trinity models

All Trinity →

Other medium models

All medium models →