SM

nisten/Biggie-SmoLlm-0.15B-Base

SmolLMGGUF by NiansuhUpdated 2024-08-07
Download on Hugging Face
Parameters152M
Context2K
Layers35
Architecturellama
Smallest quant0.2 GB
Quick answer

nisten/Biggie-SmoLlm-0.15B-Base needs about 0.9 GB of memory at Q8_0 (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.2 GB (Q8_0) to 0.4 GB (BF16).

nisten/Biggie-SmoLlm-0.15B-Base is a 152M-parameter SmolLM model in GGUF format, quantized by Niansuh. Its trained context length is 2K tokens. The repository has 3 quant files, from 0.2 GB (Q8_0) to 0.4 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.2 GB 0.7 GB
Fits Get file →
Q8_00.2 GB 0.7 GB
Fits Get file →
BF160.4 GB 0.9 GB
Fits Get file →

What GPU do you need for nisten/Biggie-SmoLlm-0.15B-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 BF16 (0.4 GB file, about 1.1 GB in use).

Which nisten/Biggie-SmoLlm-0.15B-Base quant should you choose?

Q8_0 (0.2 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q8_0 at 0.2 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters152M
Layers35
Trained context2,048 tokens
KV cache (fp16)26 KB per token

Source

Quantized byNiansuh
FamilySmolLM
Licensemit
Downloads (HF)207
Last updated2024-08-07

Frequently asked questions about nisten/Biggie-SmoLlm-0.15B-Base

How much VRAM does nisten/Biggie-SmoLlm-0.15B-Base need?

About 0.9 GB at Q8_0 with an 8K context window. That is the 0.2 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 nisten/Biggie-SmoLlm-0.15B-Base on an 8 GB GPU?

Yes, with BF16: the 0.4 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of nisten/Biggie-SmoLlm-0.15B-Base GGUF?

It depends on the quant: Q8_0 is 0.2 GB, Q8_0 is 0.2 GB, BF16 is 0.4 GB.

What context length does nisten/Biggie-SmoLlm-0.15B-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 0.2 GB at 8K and 0.1 GB at 2K.

Where can I download nisten/Biggie-SmoLlm-0.15B-Base GGUF?

The files are on Hugging Face in the Niansuh/Biggie-SmoLlm-0.15B-Base repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does nisten/Biggie-SmoLlm-0.15B-Base use?

Hugging Face lists the license as mit. 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 SmolLM-135M

Similar models

Browse all →

More from Niansuh

All by Niansuh →

More SmolLM models

All SmolLM →

Other tiny models

All tiny models →