TR

trilm 2.4b unpacked

TrilmGGUF by neopolitaUpdated 2024-09-06
Download on Hugging Face
Parameters2.46B
Context2K
Layers30
Architecturellama
Smallest quant1.0 GB
Quick answer

trilm 2.4b unpacked needs about 4.3 GB of memory at Q4_K_M (a 1.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 7 quants, from 1.0 GB (Q2_K) to 4.9 GB (F16).

trilm 2.4b unpacked is a 2.46B-parameter Trilm model in GGUF format, quantized by neopolita. Its trained context length is 2K tokens. The repository has 7 quant files, from 1.0 GB (Q2_K) to 4.9 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.0 GB 2.0 GB
Fits Get file →
Q3_K_M1.2 GB 2.3 GB
Fits Get file →
Q4_K_M1.5 GB 2.6 GB
Fits Get file →
Q5_K_M1.8 GB 2.8 GB
Fits Get file →
Q6_K2.0 GB 3.1 GB
Fits Get file →
Q8_02.6 GB 3.7 GB
Fits Get file →
F164.9 GB 6.0 GB
Fits Get file →

What GPU do you need for trilm 2.4b unpacked?

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 (1.2 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (2.6 GB file, about 5.4 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (4.9 GB file, about 7.7 GB in use).

Which trilm 2.4b unpacked quant should you choose?

Q4_K_M is the usual starting point for trilm 2.4b unpacked: it balances file size and quality well. Here it is a 1.5 GB file.

The Q8_0 file is 2.6 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 1.0 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
Parameters2.46B
Layers30
Trained context2,048 tokens
KV cache (fp16)270 KB per token

Source

Quantized byneopolita
FamilyTrilm
Licenseapache-2.0
Downloads (HF)140
Last updated2024-09-06

Frequently asked questions about trilm 2.4b unpacked

How much VRAM does trilm 2.4b unpacked need?

About 4.3 GB at Q4_K_M with an 8K context window. That is the 1.5 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 trilm 2.4b unpacked on an 8 GB GPU?

Yes, with F16: the 4.9 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of trilm 2.4b unpacked GGUF?

It depends on the quant: Q2_K is 1.0 GB, Q3_K_M is 1.2 GB, Q4_K_M is 1.5 GB, Q5_K_M is 1.8 GB, Q6_K is 2.0 GB, Q8_0 is 2.6 GB and 1 more.

What context length does trilm 2.4b unpacked support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.3 GB at 8K and 0.6 GB at 2K.

Where can I download trilm 2.4b unpacked GGUF?

The files are on Hugging Face in the neopolita/trilm_2.4b_unpacked-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 trilm 2.4b unpacked use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from neopolita

All by neopolita →

More Trilm models

All Trilm →

Other tiny models

All tiny models →