Trinity Mini Base Pre Anneal needs about 16.9 GB of memory at Q4_K_M (a 15.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.1 GB to 21.5 GB (Q6_K).
26B MoE model with 3B active parameters
Trinity Mini Base Pre Anneal is a 26B parameter AfmoeForCausalLM model with 3B active parameters. It is a pre‑anneal checkpoint trained on 8.8T tokens. The model is not suitable for general use without further finetuning.
Good at
- Domain‑specific fine‑tuning
- Enterprise‑grade LLMs
- Tinkerers’ experimentation
Limits
- Context length 4K
- Requires fine‑tuning for general use
- No vision support
Best for
- Custom chatbot development
- Enterprise data analysis
- Research prototyping
Who it’s for. Developers and researchers who need a large MoE model to fine‑tune for a specific domain. The model is ideal for those with access to GPU clusters and expertise in LLM training.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 0.8 GB | Fits | Get file → | |
| IQ1_S | 5.5 GB | 6.2 GB | Fits | Get file → | |
| IQ1_M | 6.0 GB | 6.8 GB | Fits | Get file → | |
| IQ2_XXS | 7.0 GB | 7.8 GB | Tight | Get file → | |
| IQ2_XS | 7.8 GB | 8.6 GB | Too big | Get file → | |
| IQ2_S | 7.9 GB | 8.7 GB | Too big | Get file → | |
| IQ2_M | 8.7 GB | 9.4 GB | Too big | Get file → | |
| Q2_K_S | 9.0 GB | 9.7 GB | Too big | Get file → | |
| Q2_K | 9.7 GB | 10.4 GB | Too big | Get file → | |
| IQ3_XXS | 10.2 GB | 10.9 GB | Too big | Get file → | |
| IQ3_XS | 10.8 GB | 11.6 GB | Too big | Get file → | |
| Q3_K_S | 11.4 GB | 12.2 GB | Too big | Get file → | |
| IQ3_S | 11.4 GB | 12.2 GB | Too big | Get file → | |
| IQ3_M | 11.5 GB | 12.3 GB | Too big | Get file → | |
| Q3_K_M | 12.5 GB | 13.3 GB | Too big | Get file → | |
| Q3_K_L | 13.6 GB | 14.4 GB | Too big | Get file → | |
| IQ4_XS | 14.0 GB | 14.8 GB | Too big | Get file → | |
| Q4_0 | 14.9 GB | 15.6 GB | Too big | Get file → | |
| Q4_K_S | 14.9 GB | 15.7 GB | Too big | Get file → | |
| Q4_K_M | 15.8 GB | 16.6 GB | Too big | Get file → | |
| Q4_1 | 16.4 GB | 17.2 GB | Too big | Get file → | |
| Q5_K_S | 18.0 GB | 18.8 GB | Too big | Get file → | |
| Q5_K_M | 18.6 GB | 19.3 GB | Too big | Get file → | |
| Q6_K | 21.5 GB | 22.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (5.47 GB, 6.5 GB memory). For 16 GB VRAM, Q4_K_M (15.82 GB, 16.9 GB memory) is a good balance. For 32 GB VRAM, Q5_K_M (18.56 GB, 19.6 GB memory) offers higher quality.
What GPU do you need for Trinity Mini 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 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 (7.0 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_XS (10.8 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_S (14.9 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (21.5 GB file, about 22.5 GB in use).
Which Trinity Mini Base Pre Anneal quant should you choose?
Q4_K_M is the usual starting point for Trinity Mini Base Pre Anneal: it balances file size and quality well. Here it is a 15.8 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 Mini Base Pre Anneal
How much VRAM does Trinity Mini Base Pre Anneal need?
About 16.9 GB at Q4_K_M with an 8K context window. That is the 15.8 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 Mini Base Pre Anneal on an 8 GB GPU?
Yes, with IQ2_XXS: the 7.0 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Trinity Mini Base Pre Anneal GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 5.5 GB, IQ1_M is 6.0 GB, IQ2_XXS is 7.0 GB, IQ2_XS is 7.8 GB, IQ2_S is 7.9 GB and 18 more.
What context length does Trinity Mini 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 0.3 GB at 4K.
Where can I download Trinity Mini Base Pre Anneal GGUF?
The files are on Hugging Face in the mradermacher/Trinity-Mini-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 Mini 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, the IQ1_S quant requires 5.47 GB file size and estimates 6.5 GB VRAM at 8K context.
Does the model support vision tasks?
No, the model has no vision capabilities.
What license does the model use?
The model is released under the OpenMDW-1.1 license.