harrier oss v1 27b needs about 21.2 GB of memory at Q4_K_M (a 16.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 16.6 GB (Q4_K_M) to 28.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.
Harrier OSS V1 27B – 27‑billion parameter text embedding model
Harrier OSS V1 27B is a 27‑billion parameter embedding model based on the gemma‑embedding architecture. It produces dense text embeddings using last‑token pooling and L2 normalization. The model is trained with contrastive learning on multilingual data.
Good at
- High‑quality multilingual embeddings
- Contrastive learning based representation
- Large context support
Limits
- No vision or generation capabilities
- Requires large VRAM for full context
- License is MIT – no restrictions
Best for
- Semantic search and retrieval
- Clustering and similarity tasks
- Reranking in information retrieval
Who it’s for. Developers and researchers needing high‑quality multilingual embeddings for retrieval, clustering, or semantic similarity tasks. The model is suitable for applications that can handle its large memory footprint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 16.6 GB | 21.2 GB | Too big | Get file → | |
| Q5_K_M | 19.3 GB | 23.9 GB | Too big | Get file → | |
| Q6_K | 22.2 GB | 26.8 GB | Too big | Get file → | |
| Q8_0 | 28.7 GB | 33.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 16.55 GB, estimated 21.2 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (19.28 GB, 23.9 GB memory). For 16 GB VRAM, Q6_K (22.18 GB, 26.8 GB memory). For 24 GB VRAM, Q8_0 (28.72 GB, 33.4 GB memory).
What GPU do you need for harrier oss v1 27b?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.3 GB file, about 23.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (22.2 GB file, about 26.8 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (28.7 GB file, about 33.4 GB in use).
Which harrier oss v1 27b quant should you choose?
Q4_K_M is the usual starting point for harrier oss v1 27b: it balances file size and quality well. Here it is a 16.6 GB file.
The Q8_0 file is 28.7 GB, about 1.7 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about harrier oss v1 27b
How much VRAM does harrier oss v1 27b need?
About 21.2 GB at Q4_K_M with an 8K context window. That is the 16.6 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 harrier oss v1 27b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 21.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of harrier oss v1 27b GGUF?
It depends on the quant: Q4_K_M is 16.6 GB, Q5_K_M is 19.3 GB, Q6_K is 22.2 GB, Q8_0 is 28.7 GB.
What context length does harrier oss v1 27b support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.6 GB at 32K.
Where can I download harrier oss v1 27b GGUF?
The files are on Hugging Face in the Abiray/harrier-oss-v1-27b-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 27b 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 27B on 8 GB VRAM?
Use the Q4_K_M quantization. It requires about 21.2 GB memory at 8 k context, which is beyond 8 GB VRAM, so it is not feasible on 8 GB VRAM.
What is the context length supported by this model?
The model was trained with 131072 context tokens and supports up to that length.
Does this model support vision tasks?
No, it is an embedding model and does not support vision or generation tasks.