Trinity Nano Preview needs about 4.8 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 24 quants, from 2.1 GB (IQ2_M) to 12.3 GB (BF16). 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 only 1B active per token. It is chat‑tuned and uses an AfmoeForCausalLM architecture. The model supports a 128k context length and is released under OpenMDW-1.1.
Good at
- Chat‑friendly responses
- Lightweight inference on modest GPUs
- Fast token generation
Limits
- May be unstable in some use cases
- Requires 128k context for full capability
- No vision support
Best for
- Developers testing MoE models
- Small‑scale chatbots
- Rapid prototyping on local hardware
Who it’s for. Engineers and hobbyists who want to experiment with a sparse 6B model on local hardware. The model is suitable for those who can handle potential instability and want a lightweight chat experience.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 2.1 GB | 3.1 GB | Fits | Get file → | |
| Q2_K | 2.3 GB | 3.3 GB | Fits | Get file → | |
| Q2_K_L | 2.5 GB | 3.5 GB | Fits | Get file → | |
| IQ3_XXS | 2.5 GB | 3.5 GB | Fits | Get file → | |
| IQ3_XS | 2.7 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_S | 2.8 GB | 3.8 GB | Fits | Get file → | |
| IQ3_M | 2.9 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_M | 2.9 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_L | 3.0 GB | 4.0 GB | Fits | Get file → | |
| Q3_K_XL | 3.2 GB | 4.2 GB | Fits | Get file → | |
| IQ4_XS | 3.4 GB | 4.3 GB | Fits | Get file → | |
| IQ4_NL | 3.6 GB | 4.5 GB | Fits | Get file → | |
| Q4_0 | 3.6 GB | 4.6 GB | Fits | Get file → | |
| Q4_K_S | 3.7 GB | 4.6 GB | Fits | Get file → | |
| Q4_K_M | 3.8 GB | 4.8 GB | Fits | Get file → | |
| Q4_1 | 3.9 GB | 4.9 GB | Fits | Get file → | |
| Q4_K_L | 3.9 GB | 4.9 GB | Fits | Get file → | |
| Q5_K_S | 4.3 GB | 5.3 GB | Fits | Get file → | |
| Q5_K_M | 4.4 GB | 5.4 GB | Fits | Get file → | |
| Q5_K_L | 4.5 GB | 5.5 GB | Fits | Get file → | |
| Q6_K | 5.1 GB | 6.0 GB | Fits | Get file → | |
| Q6_K_L | 5.2 GB | 6.1 GB | Fits | Get file → | |
| Q8_0 | 6.5 GB | 7.5 GB | Tight | Get file → | |
| BF16 | 12.3 GB | 13.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (est. 4.8 GB) or Q4_K_S (4.6 GB). If 6 GB VRAM is available, Q3_K_M (3.9 GB) or Q3_K_S (3.8 GB) are good choices. Larger VRAM allows Q5_K_M (5.4 GB) or Q6_K (6 GB).
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_L (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).
- 8 GB VRAM: the best quant that fits is Q8_0 (6.5 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (6.5 GB file, about 7.5 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (12.3 GB file, about 13.2 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.
The Q8_0 file is 6.5 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 IQ2_M at 2.1 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
Source
Frequently asked questions about Trinity Nano Preview
How much VRAM does Trinity Nano Preview need?
About 4.8 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 Q8_0: the 6.5 GB file needs about 7.5 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: IQ2_M is 2.1 GB, Q2_K is 2.3 GB, Q2_K_L is 2.5 GB, IQ3_XXS is 2.5 GB, IQ3_XS is 2.7 GB, Q3_K_S is 2.8 GB and 18 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 arcee-ai/Trinity-Nano-Preview-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, use a quant such as Q4_K_M or Q4_K_S which estimate 4.8 GB or 4.6 GB memory at 8k context.
Does this model support image inputs?
No, Trinity Nano Preview is a text‑only model with no vision capabilities.
What context length does it support?
The model supports a context length of 128k tokens.