Trinity Nano Base 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 Base – 6B MoE model with 1B active parameters
Trinity Nano Base is a 6.12B parameter AfmoeForCausalLM model with 1B active parameters. It supports a 128k context length and is designed for domain‑specific fine‑tuning. The model is released under the OpenMDW‑1.1 license.
Good at
- Tools integration
- Domain‑specific fine‑tuning
- Large context handling
Limits
- Not suitable for general chat without fine‑tuning
- Requires GPU with sufficient VRAM for chosen quant
- No vision support
Best for
- Enterprise custom LLMs
- Code generation with fine‑tuned data
- Math and reasoning tasks
Who it’s for. Developers and researchers who need a lightweight, Mixture‑of‑Experts model for specialized applications. The model is ideal for those who plan to train it on domain‑specific data before deployment.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.0 GB | Fits | Get file → | |
| IQ1_S | 1.4 GB | 2.4 GB | Fits | Get file → | |
| IQ1_M | 1.5 GB | 2.5 GB | Fits | Get file → | |
| IQ2_XXS | 1.7 GB | 2.7 GB | Fits | Get file → | |
| IQ2_XS | 1.9 GB | 2.9 GB | Fits | Get file → | |
| IQ2_S | 1.9 GB | 2.9 GB | Fits | Get file → | |
| IQ2_M | 2.1 GB | 3.1 GB | Fits | Get file → | |
| Q2_K_S | 2.2 GB | 3.2 GB | Fits | Get file → | |
| Q2_K | 2.3 GB | 3.3 GB | Fits | Get file → | |
| IQ3_XXS | 2.4 GB | 3.4 GB | Fits | Get file → | |
| IQ3_XS | 2.6 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_S | 2.7 GB | 3.7 GB | Fits | Get file → | |
| IQ3_S | 2.7 GB | 3.7 GB | Fits | Get file → | |
| IQ3_M | 2.8 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_M | 3.0 GB | 4.0 GB | Fits | Get file → | |
| Q3_K_L | 3.2 GB | 4.2 GB | Fits | Get file → | |
| IQ4_XS | 3.3 GB | 4.3 GB | Fits | Get file → | |
| IQ4_NL | 3.5 GB | 4.5 GB | Fits | Get file → | |
| Q4_0 | 3.5 GB | 4.5 GB | Fits | Get file → | |
| Q4_K_S | 3.5 GB | 4.5 GB | Fits | Get file → | |
| Q4_K_M | 3.8 GB | 4.7 GB | Fits | Get file → | |
| Q4_1 | 3.9 GB | 4.9 GB | Fits | Get file → | |
| Q5_K_S | 4.3 GB | 5.2 GB | Fits | Get file → | |
| Q5_K_M | 4.4 GB | 5.4 GB | Fits | Get file → | |
| Q6_K | 5.1 GB | 6.0 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (3.76 GB, 4.7 GB memory) or Q3_K_M (3 GB, 4 GB memory). If 12 GB VRAM is available, Q5_K_M (4.38 GB, 5.4 GB memory) offers higher quality. For minimal memory, IQ1_S (1.38 GB, 2.4 GB memory) is suitable.
What GPU do you need for Trinity Nano 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 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 quant should you choose?
Q4_K_M is the usual starting point for Trinity Nano Base: 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
Source
Frequently asked questions about Trinity Nano Base
How much VRAM does Trinity Nano Base 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 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 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 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 Base GGUF?
The files are on Hugging Face in the mradermacher/Trinity-Nano-Base-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 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 Base on 8 GB VRAM?
Yes, using Q4_K_M or Q3_K_M quantizations will fit within 8 GB VRAM with approximate memory usage of 4.7 GB or 4 GB respectively.
Does the model support vision tasks?
No, Trinity Nano Base does not include vision capabilities.
What is the context length of this model?
The model supports a context length of 128k tokens.