Trinity Large TrueBase i1 needs about 148.3 GB of memory at Q2_K_S (a 131.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 15 quants, from 0.5 GB to 189.3 GB (Q3_K_M).
Trinity Large TrueBase i1 – 399B‑parameter sparse MoE model
Trinity Large TrueBase i1 is a 399‑billion‑parameter sparse MoE checkpoint from Arcee AI. It was captured after 10 trillion tokens of pre‑training and contains no instruction tuning or RLHF. The model supports a 8192‑token context window.
Good at
- Large‑scale pretraining research
- Sparse MoE routing studies
- Domain‑specific fine‑tuning
Limits
- No instruction or alignment data
- No vision support
- Requires large VRAM for full precision
Best for
- Academic probing of emergent behavior
- Load‑balancing experiments
- Fine‑tuning clean foundations
Who it’s for. Researchers and developers needing a clean, large‑scale sparse MoE base for experimentation or fine‑tuning. The model is intended for academic and industrial foundation model research.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.5 GB | 1.1 GB | Fits | Get file → | |
| IQ1_S | 78.9 GB | 88.9 GB | Too big | Get file → | |
| IQ1_M | 88.1 GB | 99.2 GB | Too big | Get file → | |
| IQ2_XXS | 103.5 GB | 116.4 GB | Too big | Get file → | |
| IQ2_XS | 115.8 GB | 130.2 GB | Too big | Get file → | |
| IQ2_S | 116.3 GB | 130.8 GB | Too big | Get file → | |
| IQ2_M | 128.6 GB | 144.5 GB | Too big | Get file → | |
| Q2_K_S | 131.9 GB | 148.3 GB | Too big | Get file → | |
| Q2_K | 144.8 GB | 162.6 GB | Too big | Get file → | |
| IQ3_XXS | 153.0 GB | 171.8 GB | Too big | Get file → | |
| IQ3_XS | 161.4 GB | 181.3 GB | Too big | Get file → | |
| Q3_K_S | 171.7 GB | 192.8 GB | Too big | Get file → | |
| IQ3_S | 171.7 GB | 192.8 GB | Too big | Get file → | |
| IQ3_M | 172.2 GB | 193.4 GB | Too big | Get file → | |
| Q3_K_M | 189.3 GB | 212.5 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (0.52 GB file, 1.1 GB memory). For 16 GB VRAM, IQ1_M (78.91 GB file, 88.9 GB memory) or IQ2_XXS (103.49 GB file, 116.4 GB memory). For 32 GB VRAM, Q2_K (144.75 GB file, 162.6 GB memory) or Q3_K_M (189.31 GB file, 212.5 GB memory). Estimates are approximate.
What GPU do you need for Trinity Large TrueBase i1?
These figures add the file size, an fp16 KV cache at an 8K context window 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 (0.5 GB file, about 1.1 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
Which Trinity Large TrueBase i1 quant should you choose?
Q2_K_S (131.9 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is the first one in the table at 0.5 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 Large TrueBase i1
How much VRAM does Trinity Large TrueBase i1 need?
About 148.3 GB at Q2_K_S with an 8K context window. That is the 131.9 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 Large TrueBase i1 on an 8 GB GPU?
Yes, with the smaller files: the 0.5 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Trinity Large TrueBase i1 GGUF?
It depends on the quant: file is 0.5 GB, IQ1_S is 78.9 GB, IQ1_M is 88.1 GB, IQ2_XXS is 103.5 GB, IQ2_XS is 115.8 GB, IQ2_S is 116.3 GB and 9 more.
What context length does Trinity Large TrueBase i1 support?
The GGUF header lists a trained context length of 8,192 tokens (8K).
Where can I download Trinity Large TrueBase i1 GGUF?
The files are on Hugging Face in the mradermacher/Trinity-Large-TrueBase-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 Large TrueBase i1 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 Large TrueBase i1 on 8 GB VRAM?
Only the IQ1_S quant (0.52 GB file, 1.1 GB memory) fits within 8 GB VRAM. Larger quants exceed the limit.
Does this model support vision tasks?
No, the model has no vision capabilities.
Is there any instruction tuning included?
No, the checkpoint contains no instruction data or alignment.