TR

Triangulum 5B It

TriangulumGGUF by mradermacherUpdated 2025-01-05
Download on Hugging Face
Parameters5.41B
Context8K
Layers20
Architecturellama
Smallest quant1.5 GB
Quick answer

Triangulum 5B It 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 it – 5.41B‑parameter multilingual LLM

Triangulum 5B it is a 5.41B‑parameter LLaMA‑based model trained on synthetic long chain‑of‑thought data. It is instruction‑tuned with SFT and RLHF for improved reasoning. The model supports multilingual content generation and dialogue.

Good at

  • Reasoning with long context
  • Multilingual text generation
  • Instruction‑following

Limits

  • No vision support
  • Requires 8k context for full performance
  • CreativeML‑OpenRail‑M license

Best for

  • Chatbots needing reasoning
  • Content creation in multiple languages
  • Academic question answering

Who it’s for. Developers building multilingual conversational agents or research teams needing a reasoning‑capable LLM. The model is suitable for applications that can run on GPUs with at least 8 GB VRAM and support for GGUF quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.5 GB 2.6 GB
Fits Get file →
IQ1_M1.6 GB 2.7 GB
Fits Get file →
IQ2_XXS1.7 GB 2.9 GB
Fits Get file →
IQ2_XS1.8 GB 3.0 GB
Fits Get file →
IQ2_S1.9 GB 3.1 GB
Fits Get file →
IQ2_M2.1 GB 3.2 GB
Fits Get file →
Q2_K_S2.1 GB 3.3 GB
Fits Get file →
Q2_K2.2 GB 3.4 GB
Fits Get file →
IQ3_XXS2.3 GB 3.4 GB
Fits Get file →
IQ3_XS2.4 GB 3.6 GB
Fits Get file →
Q3_K_S2.5 GB 3.7 GB
Fits Get file →
IQ3_S2.6 GB 3.7 GB
Fits Get file →
IQ3_M2.6 GB 3.8 GB
Fits Get file →
Q3_K_M2.8 GB 3.9 GB
Fits Get file →
Q3_K_L3.0 GB 4.1 GB
Fits Get file →
IQ4_XS3.0 GB 4.2 GB
Fits Get file →
Q4_03.2 GB 4.4 GB
Fits Get file →
IQ4_NL3.2 GB 4.4 GB
Fits Get file →
Q4_K_S3.2 GB 4.4 GB
Fits Get file →
Q4_K_M3.4 GB 4.5 GB
Fits Get file →
Q4_13.5 GB 4.7 GB
Fits Get file →
Q5_K_S3.8 GB 5.0 GB
Fits Get file →
Q5_K_M3.9 GB 5.1 GB
Fits Get file →
Q6_K4.4 GB 5.6 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S (1.46 GB, 2.6 GB memory) or IQ1_M (1.55 GB, 2.7 GB memory). For 12 GB VRAM, IQ2_S (1.94 GB, 3.1 GB memory) or Q2_K (2.22 GB, 3.4 GB memory) are good choices. Higher quants like Q5_K_M (3.88 GB, 5.1 GB memory) require 16 GB VRAM or more.

What GPU do you need for Triangulum 5B It?

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 It quant should you choose?

Q4_K_M is the usual starting point for Triangulum 5B It: 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

Architecturellama
Parameters5.41B
Layers20
Trained context8,192 tokens
KV cache (fp16)80 KB per token

Source

Quantized bymradermacher
Downloads (HF)2,123
Last updated2025-01-05

Frequently asked questions about Triangulum 5B It

How much VRAM does Triangulum 5B It 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 It 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 It 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 It 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 It GGUF?

The files are on Hugging Face in the mradermacher/Triangulum-5B-it-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 It 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 it on 8 GB VRAM?

Yes, using IQ1_S or IQ1_M quants will fit within 8 GB VRAM with estimated memory usage of 2.6–2.7 GB at 8k context.

Does the model support image input?

No, Triangulum 5B it is a text‑only model with no vision capabilities.

What license applies to this model?

The model is released under the CreativeML‑OpenRail‑M license.

Other GGUFs of Triangulum-5B-it

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Triangulum models

All Triangulum →

Other small models

All small models →