TI

tinyllama 4x1.1b moe.Q5 K M

TinyllamaGGUF by thephimartUpdated 2024-01-24
Download on Hugging Face
Parameters3.38B
Context2K
Layers22
Architecturellama
Smallest quant2.4 GB
Quick answer

tinyllama 4x1.1b moe.Q5 K M needs about 3.1 GB of memory at Q5_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 4 GB GPU.

tinyllama 4x1.1b moe.Q5 K M is a 3.38B-parameter Tinyllama model in GGUF format, quantized by thephimart. Its trained context length is 2K tokens. The repository has 1 quant file, from 2.4 GB (Q5_K_M) to 2.4 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M2.4 GB 2.9 GB
Fits Get file →

What GPU do you need for tinyllama 4x1.1b moe.Q5 K M?

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 Q5_K_M (2.4 GB file, about 3.1 GB in use).

Which tinyllama 4x1.1b moe.Q5 K M quant should you choose?

Q5_K_M (2.4 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.38B (approximate, mixture of experts)
Layers22
Trained context2,048 tokens
KV cache (fp16)22 KB per token

Source

Quantized bythephimart
FamilyTinyllama
Licenseapache-2.0
Downloads (HF)43
Last updated2024-01-24

Frequently asked questions about tinyllama 4x1.1b moe.Q5 K M

How much VRAM does tinyllama 4x1.1b moe.Q5 K M need?

About 3.1 GB at Q5_K_M with an 8K context window. That is the 2.4 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 tinyllama 4x1.1b moe.Q5 K M on an 8 GB GPU?

Yes, with Q5_K_M: the 2.4 GB file needs about 3.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of tinyllama 4x1.1b moe.Q5 K M GGUF?

It depends on the quant: Q5_K_M is 2.4 GB.

What context length does tinyllama 4x1.1b moe.Q5 K M support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.0 GB at 2K.

Where can I download tinyllama 4x1.1b moe.Q5 K M GGUF?

The files are on Hugging Face in the thephimart/tinyllama-4x1.1b-moe.Q5_K_M.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 tinyllama 4x1.1b moe.Q5 K M 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 Tinyllama models

All Tinyllama →

Other tiny models

All tiny models →