Triangulum 5B needs about 4.5 GB of memory at Q4_K_M (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 1.5 GB (IQ1_S) to 4.4 GB (Q6_K).
Triangulum 5B – 5.41B‑parameter multilingual reasoning model
Triangulum 5B is a 5.41B‑parameter LLaMA‑based model trained on synthetic chain‑of‑thought data. It supports multilingual content generation and complex reasoning tasks. The model is available in multiple GGUF quantizations.
Good at
- Multilingual reasoning
- Instruction‑tuned dialogue
- Synthetic chain‑of‑thought tasks
Limits
- No vision support
- License: creativeml-openrail-m
- Requires 8k context for full performance
Best for
- Chatbots needing reasoning
- Text summarization in multiple languages
- Educational tutoring systems
Who it’s for. Developers building multilingual LLM applications that require reasoning capabilities. Researchers needing a 5B‑parameter model with instruction tuning and synthetic training data.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.5 GB | 2.6 GB | Fits | Get file → | |
| IQ1_M | 1.6 GB | 2.7 GB | Fits | Get file → | |
| IQ2_XXS | 1.7 GB | 2.9 GB | Fits | Get file → | |
| IQ2_XS | 1.8 GB | 3.0 GB | Fits | Get file → | |
| IQ2_S | 1.9 GB | 3.1 GB | Fits | Get file → | |
| IQ2_M | 2.1 GB | 3.2 GB | Fits | Get file → | |
| Q2_K_S | 2.1 GB | 3.3 GB | Fits | Get file → | |
| Q2_K | 2.2 GB | 3.4 GB | Fits | Get file → | |
| IQ3_XXS | 2.3 GB | 3.4 GB | Fits | Get file → | |
| IQ3_XS | 2.4 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_S | 2.5 GB | 3.7 GB | Fits | Get file → | |
| IQ3_S | 2.6 GB | 3.7 GB | Fits | Get file → | |
| IQ3_M | 2.6 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_M | 2.8 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_L | 3.0 GB | 4.1 GB | Fits | Get file → | |
| IQ4_XS | 3.0 GB | 4.2 GB | Fits | Get file → | |
| Q4_0 | 3.2 GB | 4.4 GB | Fits | Get file → | |
| IQ4_NL | 3.2 GB | 4.4 GB | Fits | Get file → | |
| Q4_K_S | 3.2 GB | 4.4 GB | Fits | Get file → | |
| Q4_K_M | 3.4 GB | 4.5 GB | Fits | Get file → | |
| Q4_1 | 3.5 GB | 4.7 GB | Fits | Get file → | |
| Q5_K_S | 3.8 GB | 5.0 GB | Fits | Get file → | |
| Q5_K_M | 3.9 GB | 5.1 GB | Fits | Get file → | |
| Q6_K | 4.4 GB | 5.6 GB | Fits | Get file → |
For 8 GB VRAM, use IQ1_S (file size 1.46 GB, memory 2.6 GB) or IQ1_M (1.55 GB, 2.7 GB). If 12 GB VRAM is available, IQ2_M (2.06 GB, 3.2 GB) or Q2_K (2.22 GB, 3.4 GB) are suitable. For 16 GB VRAM, consider Q3_K_M (2.76 GB, 3.9 GB) or Q4_K_M (3.35 GB, 4.5 GB).
What GPU do you need for Triangulum 5B?
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 (2.8 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (4.4 GB file, about 5.6 GB in use).
Which Triangulum 5B quant should you choose?
Q4_K_M is the usual starting point for Triangulum 5B: it balances file size and quality well. Here it is a 3.4 GB file.
If memory is tight, the smallest file is IQ1_S at 1.5 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 Triangulum 5B
How much VRAM does Triangulum 5B need?
About 4.5 GB at Q4_K_M with an 8K context window. That is the 3.4 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 Triangulum 5B on an 8 GB GPU?
Yes, with Q6_K: the 4.4 GB file needs about 5.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Triangulum 5B GGUF?
It depends on the quant: IQ1_S is 1.5 GB, IQ1_M is 1.6 GB, IQ2_XXS is 1.7 GB, IQ2_XS is 1.8 GB, IQ2_S is 1.9 GB, IQ2_M is 2.1 GB and 18 more.
What context length does Triangulum 5B support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.7 GB at 8K and 0.7 GB at 8K.
Where can I download Triangulum 5B GGUF?
The files are on Hugging Face in the mradermacher/Triangulum-5B-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 Triangulum 5B use?
Hugging Face lists the license as creativeml-openrail-m. 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 Triangulum 5B on 8 GB VRAM?
Yes, the IQ1_S and IQ1_M quantizations fit within 8 GB VRAM, using approximately 2.6–2.7 GB of memory at 8k context.
Does Triangulum 5B support image inputs?
No, the model does not include vision capabilities.
What license applies to Triangulum 5B?
The model is released under the creativeml-openrail-m license.