TR

TriLM BitNet 3 9B

TrilmGGUF by BoscoTheDogUpdated 2024-08-22
Download on Hugging Face
Parameters3.99B
Context2K
Layers30
Architecturellama
Smallest quant1.0 GB
Quick answer

TriLM BitNet 3 9B needs about 4.5 GB of memory at TQ1_0 (a 1.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 1.0 GB (TQ1_0) to 1.2 GB (TQ2_0).

TriLM BitNet 3 9B is a 3.99B-parameter Trilm model in GGUF format, quantized by BoscoTheDog. Its trained context length is 2K tokens. The repository has 2 quant files, from 1.0 GB (TQ1_0) to 1.2 GB (TQ2_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ1_01.0 GB 2.2 GB
Fits Get file →
TQ2_01.2 GB 2.4 GB
Fits Get file →

What GPU do you need for TriLM BitNet 3 9B?

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 TQ2_0 (1.2 GB file, about 4.7 GB in use).

Which TriLM BitNet 3 9B quant should you choose?

TQ1_0 (1.0 GB) is the middle option in this repository. 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
Parameters3.99B
Layers30
Trained context2,048 tokens
KV cache (fp16)360 KB per token

Source

Quantized byBoscoTheDog
FamilyTrilm
Licenseapache-2.0
Downloads (HF)41
Last updated2024-08-22

Frequently asked questions about TriLM BitNet 3 9B

How much VRAM does TriLM BitNet 3 9B need?

About 4.5 GB at TQ1_0 with an 8K context window. That is the 1.0 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 BitNet 3 9B on an 8 GB GPU?

Yes, with TQ2_0: the 1.2 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TriLM BitNet 3 9B GGUF?

It depends on the quant: TQ1_0 is 1.0 GB, TQ2_0 is 1.2 GB.

What context length does TriLM BitNet 3 9B support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 3.0 GB at 8K and 0.8 GB at 2K.

Where can I download TriLM BitNet 3 9B GGUF?

The files are on Hugging Face in the BoscoTheDog/TriLM_BitNet_3_9B_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 BitNet 3 9B 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 BoscoTheDog

All by BoscoTheDog →

More Trilm models

All Trilm →

Other small models

All small models →