qwen3 embed 8b needs about 6.3 GB of memory at Q4_K (a 4.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 4.4 GB (IQ4_XS) to 30.3 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Qwen3-Embedding-8B GGUF model for text embeddings
Qwen3-Embedding-8B is a 7.57 billion‑parameter embedding model in GGUF format. It supports 40960‑token context and 4096‑dimensional last‑token pooling. The model is licensed under apache‑2.0 and is compatible with CrispEmbed.
Good at
- High‑quality multilingual embeddings
- Large context handling
- Efficient inference with ggml
Limits
- No vision support
- Requires 8‑k context for memory estimates
- No mixture of experts
Best for
- Text retrieval pipelines
- Embedding‑based clustering
- Code‑to‑text similarity
Who it’s for. Developers building embedding‑centric applications who need a compact, open‑source model. The model is suitable for research and production use where an apache‑2.0 license is acceptable.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 4.4 GB | 6.1 GB | Fits | Get file → | |
| Q4_K | 4.6 GB | 6.3 GB | Fits | Get file → | |
| Q4_K | 4.6 GB | 6.3 GB | Fits | Get file → | |
| Q5_K | 5.4 GB | 7.2 GB | Fits | Get file → | |
| Q8_0 | 8.0 GB | 9.8 GB | Too big | Get file → | |
| — | 30.3 GB | 32.0 GB | Too big | Get file → |
For 8 GB VRAM, Q4_K (file size 4.57 GB, estimated 6.3 GB memory) is recommended. For 6 GB VRAM, IQ4_XS (4.36 GB, 6.1 GB memory) is a close fit. Larger memory budgets can use Q5_K or Q8_0.
What GPU do you need for qwen3 embed 8b?
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: the best quant that fits is Q5_K (5.4 GB file, about 7.2 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.8 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (30.3 GB file, about 32.0 GB in use).
Which qwen3 embed 8b quant should you choose?
Q4_K (4.6 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is IQ4_XS at 4.4 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
Source
Frequently asked questions about qwen3 embed 8b
How much VRAM does qwen3 embed 8b need?
About 6.3 GB at Q4_K with an 8K context window. That is the 4.6 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 qwen3 embed 8b on an 8 GB GPU?
Yes, with Q5_K: the 5.4 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of qwen3 embed 8b GGUF?
It depends on the quant: IQ4_XS is 4.4 GB, Q4_K is 4.6 GB, Q4_K is 4.6 GB, Q5_K is 5.4 GB, Q8_0 is 8.0 GB, file is 30.3 GB.
What context length does qwen3 embed 8b support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download qwen3 embed 8b GGUF?
The files are on Hugging Face in the cstr/qwen3-embed-8b-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 qwen3 embed 8b 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.
Can I run Qwen3-Embedding-8B on 8 GB VRAM?
Yes, the Q4_K quantization uses about 6.3 GB of VRAM at 8‑k context, leaving headroom for other processes.
What license does this model use?
The model is distributed under the apache‑2.0 license, identical to the upstream Qwen3-Embedding-8B.
What is the embedding dimensionality?
The model outputs 4096‑dimensional vectors using last‑token pooling.