SM

SmolLM 1.7B Instruct

SmolLMGGUF by SandLogicTechnologiesUpdated 2024-09-10
Download on Hugging Face
Parameters1.71B
Context2K
Layers24
Architecturellama
Smallest quant0.9 GB
Quick answer

SmolLM 1.7B Instruct needs about 3.2 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.9 GB (IQ4_XS) to 1.2 GB (Q5_K_M).

SmolLM 1.7B Instruct is a 1.71B-parameter SmolLM model in GGUF format, quantized by SandLogicTechnologies. Its trained context length is 2K tokens. The repository has 3 quant files, from 0.9 GB (IQ4_XS) to 1.2 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS0.9 GB 1.9 GB
Fits Get file →
Q4_K_M1.1 GB 2.0 GB
Fits Get file →
Q5_K_M1.2 GB 2.1 GB
Fits Get file →

What GPU do you need for SmolLM 1.7B Instruct?

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 (1.2 GB file, about 3.3 GB in use).

Which SmolLM 1.7B Instruct quant should you choose?

Q4_K_M is the usual starting point for SmolLM 1.7B Instruct: it balances file size and quality well. Here it is a 1.1 GB file.

If memory is tight, the smallest file is IQ4_XS at 0.9 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.71B
Layers24
Trained context2,048 tokens
KV cache (fp16)192 KB per token

Source

FamilySmolLM
Licenseapache-2.0
Downloads (HF)125
Last updated2024-09-10

Frequently asked questions about SmolLM 1.7B Instruct

How much VRAM does SmolLM 1.7B Instruct need?

About 3.2 GB at Q4_K_M with an 8K context window. That is the 1.1 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 SmolLM 1.7B Instruct on an 8 GB GPU?

Yes, with Q5_K_M: the 1.2 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SmolLM 1.7B Instruct GGUF?

It depends on the quant: IQ4_XS is 0.9 GB, Q4_K_M is 1.1 GB, Q5_K_M is 1.2 GB.

What context length does SmolLM 1.7B Instruct 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 SmolLM 1.7B Instruct GGUF?

The files are on Hugging Face in the SandLogicTechnologies/SmolLM-1.7B-Instruct-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 SmolLM 1.7B Instruct 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 SmolLM-1.7B-Instruct

Similar models

Browse all →

More from SandLogicTechnologies

All by SandLogicTechnologies →

More SmolLM models

All SmolLM →

Other tiny models

All tiny models →