MO

mobilellama

MobilellamaGGUF by 21worldUpdated 2024-01-04
Download on Hugging Face
Parameters2.7B
Context2K
Layers32
Architecturellama
Smallest quant1.2 GB
Quick answer

mobilellama needs about 4.7 GB of memory at Q4_K_S (a 1.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 1.2 GB (Q3_K_S) to 2.9 GB (Q8_0).

mobilellama is a 2.7B-parameter Mobilellama model in GGUF format, quantized by 21world. Its trained context length is 2K tokens. The repository has 3 quant files, from 1.2 GB (Q3_K_S) to 2.9 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S1.2 GB 2.4 GB
Fits Get file →
Q4_K_S1.6 GB 2.7 GB
Fits Get file →
Q8_02.9 GB 4.0 GB
Fits Get file →

What GPU do you need for mobilellama?

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 Q4_K_S (1.6 GB file, about 4.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (2.9 GB file, about 6.1 GB in use).

Which mobilellama quant should you choose?

Q4_K_S (1.6 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q3_K_S at 1.2 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters2.7B
Layers32
Trained context2,048 tokens
KV cache (fp16)320 KB per token

Source

Quantized by21world
Downloads (HF)55
Last updated2024-01-04

Frequently asked questions about mobilellama

How much VRAM does mobilellama need?

About 4.7 GB at Q4_K_S with an 8K context window. That is the 1.6 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 mobilellama on an 8 GB GPU?

Yes, with Q8_0: the 2.9 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mobilellama GGUF?

It depends on the quant: Q3_K_S is 1.2 GB, Q4_K_S is 1.6 GB, Q8_0 is 2.9 GB.

What context length does mobilellama support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.

Where can I download mobilellama GGUF?

The files are on Hugging Face in the 21world/MobileLLaMA-2.7B-Chat.GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from 21world

All by 21world →

More Mobilellama models

All Mobilellama →

Other tiny models

All tiny models →