TR

TriLM_1.1B_Unpacked

TrilmGGUF by MungertUpdated 2025-09-24
Download on Hugging Face
Parameters1.15B
Context2K
Layers24
Architecturellama
Smallest quant0.3 GB
Quick answer

TriLM_1.1B_Unpacked needs about 2.6 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 27 quants, from 0.3 GB (TQ1_0) to 2.3 GB (BF16).

TriLM_1.1B_Unpacked is a 1.15B-parameter Trilm model in GGUF format, quantized by Mungert. Its trained context length is 2K tokens. The repository has 27 quant files, from 0.3 GB (TQ1_0) to 2.3 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ1_00.3 GB 1.2 GB
Fits Get file →
TQ2_00.4 GB 1.2 GB
Fits Get file →
IQ3_XXS0.5 GB 1.3 GB
Fits Get file →
IQ3_XS0.5 GB 1.4 GB
Fits Get file →
IQ3_S0.5 GB 1.4 GB
Fits Get file →
Q3_K_S0.5 GB 1.4 GB
Fits Get file →
IQ3_M0.6 GB 1.4 GB
Fits Get file →
Q3_K_M0.6 GB 1.4 GB
Fits Get file →
IQ4_XS0.6 GB 1.5 GB
Fits Get file →
Q4_00.6 GB 1.5 GB
Fits Get file →
IQ4_NL0.7 GB 1.5 GB
Fits Get file →
Q4_K_S0.7 GB 1.6 GB
Fits Get file →
Q4_10.7 GB 1.6 GB
Fits Get file →
Q4_K_M0.7 GB 1.6 GB
Fits Get file →
Q5_00.8 GB 1.6 GB
Fits Get file →
Q5_K_S0.8 GB 1.7 GB
Fits Get file →
Q5_K_M0.8 GB 1.7 GB
Fits Get file →
Q5_10.9 GB 1.7 GB
Fits Get file →
Q6_K_M0.9 GB 1.8 GB
Fits Get file →
BF160.9 GB 1.8 GB
Fits Get file →
F160.9 GB 1.8 GB
Fits Get file →
BF161.2 GB 2.0 GB
Fits Get file →
F161.2 GB 2.0 GB
Fits Get file →
Q8_01.2 GB 2.1 GB
Fits Get file →
BF161.4 GB 2.2 GB
Fits Get file →
F161.4 GB 2.2 GB
Fits Get file →
BF162.3 GB 3.2 GB
Fits Get file →

What GPU do you need for TriLM_1.1B_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 BF16 (1.4 GB file, about 3.3 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (2.3 GB file, about 4.2 GB in use).

Which TriLM_1.1B_Unpacked quant should you choose?

Q4_K_M is the usual starting point for TriLM_1.1B_Unpacked: it balances file size and quality well. Here it is a 0.7 GB file.

The Q8_0 file is 1.2 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 TQ1_0 at 0.3 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.15B
Layers24
Trained context2,048 tokens
KV cache (fp16)168 KB per token

Source

Quantized byMungert
FamilyTrilm
Licenseapache-2.0
Downloads (HF)116
Last updated2025-09-24

Frequently asked questions about TriLM_1.1B_Unpacked

How much VRAM does TriLM_1.1B_Unpacked need?

About 2.6 GB at Q4_K_M with an 8K context window. That is the 0.7 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_1.1B_Unpacked on an 8 GB GPU?

Yes, with BF16: the 2.3 GB file needs about 4.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TriLM_1.1B_Unpacked GGUF?

It depends on the quant: TQ1_0 is 0.3 GB, TQ2_0 is 0.4 GB, IQ3_XXS is 0.5 GB, IQ3_XS is 0.5 GB, IQ3_S is 0.5 GB, Q3_K_S is 0.5 GB and 21 more.

What context length does TriLM_1.1B_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 1.4 GB at 8K and 0.4 GB at 2K.

Where can I download TriLM_1.1B_Unpacked GGUF?

The files are on Hugging Face in the Mungert/TriLM_1.1B_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_1.1B_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 Mungert

All by Mungert →

More Trilm models

All Trilm →

Other tiny models

All tiny models →