HA

haru 180m

HaruGGUF by aixkUpdated 2026-05-11
Download on Hugging Face
Parameters184M
Context8K
Layers44
Architecturellama
Smallest quant0.1 GB
Quick answer

haru 180m needs about 0.9 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.1 GB (IQ1_S) to 0.4 GB (F16).

haru 180m is a 184M-parameter Haru model in GGUF format, quantized by aixk. Its trained context length is 8K tokens. The repository has 5 quant files, from 0.1 GB (IQ1_S) to 0.4 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.1 GB 0.9 GB
Fits Get file →
IQ2_XXS0.1 GB 0.9 GB
Fits Get file →
Q3_K_M0.1 GB 0.9 GB
Fits Get file →
Q4_K_M0.1 GB 0.9 GB
Fits Get file →
F160.4 GB 1.1 GB
Fits Get file →

What GPU do you need for haru 180m?

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 (0.4 GB file, about 1.1 GB in use).

Which haru 180m quant should you choose?

Q4_K_M is the usual starting point for haru 180m: it balances file size and quality well. Here it is a 0.1 GB file.

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
Parameters184M
Layers44
Trained context8,192 tokens
KV cache (fp16)33 KB per token

Source

Quantized byaixk
FamilyHaru
Downloads (HF)65
Last updated2026-05-11

Frequently asked questions about haru 180m

How much VRAM does haru 180m need?

About 0.9 GB at Q4_K_M 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 haru 180m on an 8 GB GPU?

Yes, with F16: 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 haru 180m GGUF?

It depends on the quant: IQ1_S is 0.1 GB, IQ2_XXS is 0.1 GB, Q3_K_M is 0.1 GB, Q4_K_M is 0.1 GB, F16 is 0.4 GB.

What context length does haru 180m support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.3 GB at 8K.

Where can I download haru 180m GGUF?

The files are on Hugging Face in the aixk/haru-180m-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from aixk

All by aixk →

More Haru models

All Haru →

Other tiny models

All tiny models →