MO

MobileLLaMA 1.4B Base

MobilellamaGGUF by andrijdavidUpdated 2024-01-02
Download on Hugging Face
Parameters1.36B
Context2K
Layers24
Architecturellama
Smallest quant0.6 GB
Quick answer

MobileLLaMA 1.4B Base needs about 2.9 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 18 quants, from 0.6 GB (Q2_K) to 2.7 GB (F16).

MobileLLaMA 1.4B Base – lightweight Llama model in GGUF format

MobileLLaMA 1.4B Base is a 1.36B‑parameter Llama model optimized for local inference. It supports a 2048‑token context window and is released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations for varied memory budgets.

Good at

  • Fast inference on modest GPUs
  • Low VRAM footprint
  • Compact model size

Limits

  • No vision capabilities
  • Context limited to 2048 tokens
  • Requires GPU for best performance

Best for

  • Local chat applications
  • Edge device inference
  • Rapid prototyping

Who it’s for. Developers and hobbyists who need a small, efficient Llama model for local use. The model is suitable for projects that require quick deployment without large GPU resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.6 GB 1.5 GB
Fits Get file →
Q3_K_S0.6 GB 1.5 GB
Fits Get file →
Q3_K0.7 GB 1.6 GB
Fits Get file →
Q3_K_M0.7 GB 1.6 GB
Fits Get file →
Q3_K_L0.7 GB 1.6 GB
Fits Get file →
Q4_00.8 GB 1.7 GB
Fits Get file →
Q4_K_S0.8 GB 1.7 GB
Fits Get file →
Q4_K0.8 GB 1.7 GB
Fits Get file →
Q4_K_M0.8 GB 1.7 GB
Fits Get file →
Q4_10.9 GB 1.8 GB
Fits Get file →
Q5_00.9 GB 1.9 GB
Fits Get file →
Q5_K_S0.9 GB 1.9 GB
Fits Get file →
Q5_K1.0 GB 1.9 GB
Fits Get file →
Q5_K_M1.0 GB 1.9 GB
Fits Get file →
Q5_11.0 GB 1.9 GB
Fits Get file →
Q6_K1.1 GB 2.0 GB
Fits Get file →
Q8_01.5 GB 2.4 GB
Fits Get file →
F162.7 GB 3.6 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M (0.84 GB file, ~2.9 GB VRAM at 8 k context) is a good balance. For 4 GB VRAM, Q2_K (0.59 GB file, ~2.7 GB VRAM) is recommended. For higher precision, Q5_K_M (0.97 GB file, ~3.1 GB VRAM) can be used if memory allows.

What GPU do you need for MobileLLaMA 1.4B Base?

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 Q8_0 (1.5 GB file, about 3.6 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (2.7 GB file, about 4.8 GB in use).

Which MobileLLaMA 1.4B Base quant should you choose?

Q4_K_M is the usual starting point for MobileLLaMA 1.4B Base: it balances file size and quality well. Here it is a 0.8 GB file.

The Q8_0 file is 1.5 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 0.6 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
Parameters1.36B
Layers24
Trained context2,048 tokens
KV cache (fp16)192 KB per token

Source

Quantized byandrijdavid
Licenseapache-2.0
Downloads (HF)764
Last updated2024-01-02

Frequently asked questions about MobileLLaMA 1.4B Base

How much VRAM does MobileLLaMA 1.4B Base need?

About 2.9 GB at Q4_K_M with an 8K context window. That is the 0.8 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 1.4B Base on an 8 GB GPU?

Yes, with F16: the 2.7 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MobileLLaMA 1.4B Base GGUF?

It depends on the quant: Q2_K is 0.6 GB, Q3_K_S is 0.6 GB, Q3_K is 0.7 GB, Q3_K_M is 0.7 GB, Q3_K_L is 0.7 GB, Q4_0 is 0.8 GB and 12 more.

What context length does MobileLLaMA 1.4B Base support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.4 GB at 2K.

Where can I download MobileLLaMA 1.4B Base GGUF?

The files are on Hugging Face in the andrijdavid/MobileLLaMA-1.4B-Base-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 MobileLLaMA 1.4B Base 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.

Can I run MobileLLaMA 1.4B Base on 8 GB VRAM?

Yes, using Q4_K_M or Q4_K_S will fit within 8 GB VRAM with some headroom for buffers.

Does this model support vision tasks?

No, MobileLLaMA 1.4B Base is a text‑only model with no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing free use and modification.

Similar models

Browse all →

More from andrijdavid

All by andrijdavid →

More Mobilellama models

All Mobilellama →

Other tiny models

All tiny models →