Triplex needs about 6.1 GB of memory at Q4_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 14 quants, from 1.4 GB (Q2_K) to 4.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.
Triplex – a Phi3‑based LLM for knowledge graph construction
Triplex is a 3.82B‑parameter model fine‑tuned from Phi3‑3.8B for extracting triplets from unstructured data. It supports a 131072‑token context window and is optimized for local knowledge graph building. The model is released under a cc‑by‑nc‑sa‑4.0 license.
Good at
- Extracting subject‑predicate‑object triplets
- Building knowledge graphs locally
- Reducing graph construction cost
Limits
- No vision support
- Commercial use restricted by revenue
- Large context requires significant VRAM
Best for
- Local knowledge graph creation
- RAG pipelines with graph backends
- Research on graph extraction
Who it’s for. Researchers and developers needing efficient, local knowledge graph construction. The model is suitable for academic projects and small‑scale commercial use under the license terms.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.4 GB | 5.1 GB | Fits | Get file → | |
| Q3_K_S | 1.7 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_M | 2.0 GB | 5.7 GB | Fits | Get file → | |
| Q3_K_L | 2.1 GB | 5.8 GB | Fits | Get file → | |
| Q4_0 | 2.2 GB | 5.9 GB | Fits | Get file → | |
| Q4_K_S | 2.2 GB | 5.9 GB | Fits | Get file → | |
| Q4_K_M | 2.4 GB | 6.1 GB | Fits | Get file → | |
| Q4_1 | 2.4 GB | 6.1 GB | Fits | Get file → | |
| Q5_0 | 2.6 GB | 6.4 GB | Fits | Get file → | |
| Q5_K_S | 2.6 GB | 6.4 GB | Fits | Get file → | |
| Q5_K_M | 2.8 GB | 6.5 GB | Fits | Get file → | |
| Q5_1 | 2.9 GB | 6.6 GB | Fits | Get file → | |
| Q6_K | 3.1 GB | 6.9 GB | Fits | Get file → | |
| Q8_0 | 4.1 GB | 7.8 GB | Tight | Get file → |
For 8 GB VRAM, use Q2_K (file size 1.42 GB, estimated 5.1 GB memory). For 12 GB VRAM, Q4_K_M (file size 2.39 GB, estimated 6.1 GB memory) is a good balance. For 16 GB VRAM, Q5_K_M (file size 2.82 GB, estimated 6.5 GB memory) offers higher precision.
What GPU do you need for Triplex?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q4_K_S (2.2 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 7.8 GB in use).
Which Triplex quant should you choose?
Q4_K_M is the usual starting point for Triplex: it balances file size and quality well. Here it is a 2.4 GB file.
The Q8_0 file is 4.1 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 Q2_K at 1.4 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 Triplex
How much VRAM does Triplex need?
About 6.1 GB at Q4_K_M with an 8K context window. That is the 2.4 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 Triplex on an 8 GB GPU?
Yes, with Q8_0: the 4.1 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Triplex GGUF?
It depends on the quant: Q2_K is 1.4 GB, Q3_K_S is 1.7 GB, Q3_K_M is 2.0 GB, Q3_K_L is 2.1 GB, Q4_0 is 2.2 GB, Q4_K_S is 2.2 GB and 8 more.
What context length does Triplex support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.
Where can I download Triplex GGUF?
The files are on Hugging Face in the QuantFactory/Triplex-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 Triplex use?
Hugging Face lists the license as cc-by-nc-sa-4.0. 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 Triplex on 8 GB VRAM?
Yes, the Q2_K quantized model requires about 5.1 GB memory at 8 k context, fitting within 8 GB VRAM.
Is Triplex suitable for commercial use?
Commercial use is allowed for organizations with under $5 M USD revenue; otherwise contact the team to waive restrictions.
Does Triplex support vision tasks?
No, Triplex is a text‑only model and does not support vision inputs.