IN

InstructLM 500M

InstructlmGGUF by DevQuasar-3Updated 2024-12-04
Download on Hugging Face
Parameters568M
Context2K
Layers16
Architecturellama
Smallest quant0.6 GB
Quick answer

InstructLM 500M needs about 1.9 GB of memory at Q8_0 (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.6 GB (Q8_0) to 1.1 GB (F16).

InstructLM 500M is a 568M-parameter Instructlm model in GGUF format, quantized by DevQuasar-3. Its trained context length is 2K tokens. The repository has 2 quant files, from 0.6 GB (Q8_0) to 1.1 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.6 GB 1.3 GB
Fits Get file →
F161.1 GB 1.8 GB
Fits Get file →

What GPU do you need for InstructLM 500M?

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 F16 (1.1 GB file, about 2.4 GB in use).

Which InstructLM 500M quant should you choose?

Q8_0 (0.6 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters568M
Layers16
Trained context2,048 tokens
KV cache (fp16)96 KB per token

Source

Quantized byDevQuasar-3
Licenseapache-2.0
Downloads (HF)23
Last updated2024-12-04

Frequently asked questions about InstructLM 500M

How much VRAM does InstructLM 500M need?

About 1.9 GB at Q8_0 with an 8K context window. That is the 0.6 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 InstructLM 500M on an 8 GB GPU?

Yes, with F16: the 1.1 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of InstructLM 500M GGUF?

It depends on the quant: Q8_0 is 0.6 GB, F16 is 1.1 GB.

What context length does InstructLM 500M support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.2 GB at 2K.

Where can I download InstructLM 500M GGUF?

The files are on Hugging Face in the DevQuasar-3/InstructLM-500M-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 InstructLM 500M 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.

Similar models

Browse all →

More from DevQuasar-3

All by DevQuasar-3 →

More Instructlm models

All Instructlm →

Other tiny models

All tiny models →