LL

gguf Smol Llama 101M Chat v1

LlamaGGUF by FelladrinUpdated 2024-07-26
Download on Hugging Face
Parameters101M
Context1K
Layers6
Architecturellama
Smallest quant0.1 GB
Quick answer

gguf Smol Llama 101M Chat v1 needs about 0.6 GB of memory at IQ4_XS (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 8 quants, from 0.1 GB (IQ1_S) to 0.2 GB.

gguf Smol Llama 101M Chat v1 is a 101M-parameter Llama model in GGUF format, quantized by Felladrin. Its trained context length is 1K tokens. The repository has 8 quant files, from 0.1 GB (IQ1_S) to 0.2 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.1 GB 0.6 GB
Fits Get file →
IQ2_XXS0.1 GB 0.6 GB
Fits Get file →
IQ3_XXS0.1 GB 0.6 GB
Fits Get file →
IQ4_XS0.1 GB 0.6 GB
Fits Get file →
Q5_K0.1 GB 0.6 GB
Fits Get file →
Q6_K0.1 GB 0.6 GB
Fits Get file →
Q8_00.1 GB 0.6 GB
Fits Get file →
—0.2 GB 0.7 GB
Fits Get file →

What GPU do you need for gguf Smol Llama 101M Chat v1?

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 the main file (0.2 GB file, about 0.8 GB in use).

Which gguf Smol Llama 101M Chat v1 quant should you choose?

IQ4_XS (0.1 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 IQ1_S at 0.1 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
Parameters101M
Layers6
Trained context1,024 tokens
KV cache (fp16)6 KB per token

Source

Quantized byFelladrin
FamilyLlama
Licenseapache-2.0
Downloads (HF)111
Last updated2024-07-26

Frequently asked questions about gguf Smol Llama 101M Chat v1

How much VRAM does gguf Smol Llama 101M Chat v1 need?

About 0.6 GB at IQ4_XS with an 8K context window. That is the 0.1 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 gguf Smol Llama 101M Chat v1 on an 8 GB GPU?

Yes, with the smaller files: the 0.2 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gguf Smol Llama 101M Chat v1 GGUF?

It depends on the quant: IQ1_S is 0.1 GB, IQ2_XXS is 0.1 GB, IQ3_XXS is 0.1 GB, IQ4_XS is 0.1 GB, Q5_K is 0.1 GB, Q6_K is 0.1 GB and 2 more.

What context length does gguf Smol Llama 101M Chat v1 support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 1K.

Where can I download gguf Smol Llama 101M Chat v1 GGUF?

The files are on Hugging Face in the Felladrin/gguf-Smol-Llama-101M-Chat-v1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does gguf Smol Llama 101M Chat v1 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.

Other GGUFs of Smol-Llama-101M-Chat-v1

Similar models

Browse all →

More from Felladrin

All by Felladrin →

More Llama models

All Llama →

Other tiny models

All tiny models →