Harrier Oss v1 0.6b needs about 1.8 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.3 GB (Q2_K) to 1.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Harrier Oss v1 0.6b – 0.6 B parameter Qwen3 text‑embedding model
Harrier Oss v1 0.6b is a 0.6 B parameter decoder‑only Qwen3 model optimized for multilingual text embeddings. It supports 32 768 token context and is released under the MIT license. The model is available in multiple GGUF quantizations for efficient inference.
Good at
- Multilingual text embeddings
- Contrastive retrieval tasks
- Semantic similarity
Limits
- No vision support
- Requires instruction prompt for queries
- Large VRAM needed for full precision
Best for
- Embedding search engines
- Document clustering
- Semantic search pipelines
Who it’s for. Developers building multilingual embedding services or research teams needing a compact, open‑source embedding model. The model is suitable for use with llama.cpp or other GGUF‑compatible inference engines.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.3 GB | 1.7 GB | Fits | Get file → | |
| Q3_K_S | 0.3 GB | 1.8 GB | Fits | Get file → | |
| Q3_K_M | 0.3 GB | 1.8 GB | Fits | Get file → | |
| Q3_K_L | 0.4 GB | 1.8 GB | Fits | Get file → | |
| IQ4_XS | 0.4 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_S | 0.4 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_M | 0.4 GB | 1.8 GB | Fits | Get file → | |
| Q5_K_S | 0.4 GB | 1.9 GB | Fits | Get file → | |
| Q5_K_M | 0.4 GB | 1.9 GB | Fits | Get file → | |
| Q6_K | 0.5 GB | 1.9 GB | Fits | Get file → | |
| Q8_0 | 0.6 GB | 2.1 GB | Fits | Get file → | |
| F16 | 1.2 GB | 2.6 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.4 GB, ~1.8 GB VRAM) or Q5_K_S (0.44 GB, ~1.9 GB VRAM). For 4 GB VRAM, Q3_K_S (0.32 GB, ~1.8 GB VRAM) or Q2_K (0.3 GB, ~1.7 GB VRAM) are recommended. Full precision F16 requires ~2.6 GB VRAM.
What GPU do you need for Harrier Oss v1 0.6b?
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 (1.2 GB file, about 2.6 GB in use).
Which Harrier Oss v1 0.6b quant should you choose?
Q4_K_M is the usual starting point for Harrier Oss v1 0.6b: it balances file size and quality well. Here it is a 0.4 GB file.
The Q8_0 file is 0.6 GB, about 1.6 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 Q2_K at 0.3 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
Source
Frequently asked questions about Harrier Oss v1 0.6b
How much VRAM does Harrier Oss v1 0.6b need?
About 1.8 GB at Q4_K_M with an 8K context window. That is the 0.4 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 0.6b on an 8 GB GPU?
Yes, with F16: the 1.2 GB file needs about 2.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Harrier Oss v1 0.6b GGUF?
It depends on the quant: Q2_K is 0.3 GB, Q3_K_S is 0.3 GB, Q3_K_M is 0.3 GB, Q3_K_L is 0.4 GB, IQ4_XS is 0.4 GB, Q4_K_S is 0.4 GB and 6 more.
What context length does Harrier Oss v1 0.6b support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download Harrier Oss v1 0.6b GGUF?
The files are on Hugging Face in the mradermacher/harrier-oss-v1-0.6b-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 0.6b 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 0.6b on 8 GB VRAM?
Yes, using Q4_K_M or Q5_K_S quantizations keeps VRAM usage below 2 GB, leaving headroom for other processes.
Does the model support image inputs?
No, Harrier Oss v1 0.6b is a text‑only embedding model and does not process visual data.
What license applies to this model?
The model is released under the MIT license, allowing free use and modification.