ON

ondevice llm

OndeviceGGUF by MislamdevUpdated 2026-01-16
Download on Hugging Face
Parameters127M
Context32K
Layers18
Architecturegemma3
Smallest quant0.1 GB
Quick answer

ondevice llm needs about 0.9 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.1 GB (Q4_K_S) to 0.6 GB (Q4_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 0.6 GB.

ondevice llm is a 127M-parameter Ondevice model in GGUF format, quantized by Mislamdev. Its trained context length is 32K tokens. The repository has 4 quant files, from 0.1 GB (Q4_K_S) to 0.6 GB (Q4_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S0.1 GB 0.8 GB
Fits Get file →
Q8_00.1 GB 0.8 GB
Fits Get file →
Q4_K_M0.3 GB 0.9 GB
Fits Get file →
Q4_K_S0.6 GB 1.3 GB
Fits Get file →

What GPU do you need for ondevice llm?

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 Q4_K_S (0.6 GB file, about 1.3 GB in use).

Which ondevice llm quant should you choose?

Q4_K_M is the usual starting point for ondevice llm: it balances file size and quality well. Here it is a 0.3 GB file.

The Q8_0 file is 0.1 GB, about 0.5 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 Q4_K_S at 0.1 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

Architecturegemma3
Parameters127M
Layers18
Trained context32,768 tokens
KV cache (fp16)18 KB per token

Source

Quantized byMislamdev
FamilyOndevice
Licenseapache-2.0
Downloads (HF)14
Last updated2026-01-16

Frequently asked questions about ondevice llm

How much VRAM does ondevice llm need?

About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.3 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 ondevice llm on an 8 GB GPU?

Yes, with Q4_K_S: the 0.6 GB file needs about 1.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ondevice llm GGUF?

It depends on the quant: Q4_K_S is 0.1 GB, Q8_0 is 0.1 GB, Q4_K_M is 0.3 GB, Q4_K_S is 0.6 GB.

What context length does ondevice llm support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.6 GB at 32K.

Where can I download ondevice llm GGUF?

The files are on Hugging Face in the Mislamdev/ondevice-llm-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 ondevice llm 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 →

Other tiny models

All tiny models →