HA

Harrier Oss v1 270m

HarrierGGUF by mykorUpdated 2026-03-31
Download on Hugging Face
Parameters268M
Context32K
Layers18
Architecturegemma3
Smallest quant0.2 GB
Quick answer

Harrier Oss v1 270m 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 6 quants, from 0.2 GB (Q3_K_L) to 0.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.6 GB.

Harrier Oss v1 270m – a 0.268B multilingual text embedding model

Harrier Oss v1 270m is a decoder‑only gemma3 architecture designed for dense text embeddings. It supports 32768 context tokens and is released under the MIT license. The model excels in retrieval, clustering, and semantic similarity tasks.

Good at

  • Dense text embeddings
  • Multilingual retrieval
  • Semantic similarity

Limits

  • No vision support
  • No mixture of experts
  • Limited to 32768 context tokens

Best for

  • Information retrieval pipelines
  • Semantic search engines
  • Embedding‑based clustering

Who it’s for. Developers building multilingual search or recommendation systems that require compact embeddings. Researchers needing a lightweight, open‑source embedding model for experimentation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L0.2 GB 0.9 GB
Fits Get file →
Q4_K_M0.3 GB 0.9 GB
Fits Get file →
Q5_K_M0.3 GB 0.9 GB
Fits Get file →
Q6_K0.3 GB 0.9 GB
Fits Get file →
Q8_00.3 GB 0.9 GB
Fits Get file →
BF160.5 GB 1.2 GB
Fits Get file →

For 8 GB VRAM, use Q3_K_L, Q4_K_M, or Q5_K_M – each file is 0.25–0.26 GB and needs about 0.9 GB memory at 8 k context. For 16 GB VRAM, Q6_K or Q8_0 (0.28–0.29 GB) are suitable. BF16 (0.54 GB) requires about 1.2 GB memory and is best for higher precision needs.

What GPU do you need for Harrier Oss v1 270m?

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

Which Harrier Oss v1 270m quant should you choose?

Q4_K_M is the usual starting point for Harrier Oss v1 270m: it balances file size and quality well. Here it is a 0.3 GB file.

The Q8_0 file is 0.3 GB, about 1.2 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 Q3_K_L at 0.2 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters268M
Layers18
Trained context32,768 tokens
KV cache (fp16)18 KB per token

Source

Quantized bymykor
FamilyHarrier
Licensemit
Downloads (HF)508
Last updated2026-03-31

Frequently asked questions about Harrier Oss v1 270m

How much VRAM does Harrier Oss v1 270m 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 Harrier Oss v1 270m on an 8 GB GPU?

Yes, with BF16: the 0.5 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Harrier Oss v1 270m GGUF?

It depends on the quant: Q3_K_L is 0.2 GB, Q4_K_M is 0.3 GB, Q5_K_M is 0.3 GB, Q6_K is 0.3 GB, Q8_0 is 0.3 GB, BF16 is 0.5 GB.

What context length does Harrier Oss v1 270m 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 Harrier Oss v1 270m GGUF?

The files are on Hugging Face in the mykor/harrier-oss-v1-270m-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 Harrier Oss v1 270m 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.

Can I run Harrier Oss v1 270m on 8 GB VRAM?

Yes, the Q3_K_L, Q4_K_M, and Q5_K_M quantizations fit within 8 GB VRAM, each using roughly 0.9 GB memory at 8 k context.

Does this model support vision tasks?

No, Harrier Oss v1 270m is a text‑only embedding model with no vision capabilities.

What license applies to this model?

The model is released under the MIT license, allowing free use and modification.

Other GGUFs of harrier-oss-v1-270m

Similar models

Browse all →

More from mykor

All by mykor →

More Harrier models

All Harrier →

Other tiny models

All tiny models →