bge-large-zh-v1.5 needs about 1.5 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.2 GB (Q4_K_M) to 1.3 GB (F32).
bge-large-zh-v1.5: 0.324B parameter embedding model in GGUF format
bge-large-zh-v1.5 is a 0.324B parameter BERT-based embedding model. It supports 512 token context and is released under the MIT license. The model is available in multiple GGUF quantizations for efficient inference.
Good at
- Embedding generation
- Text similarity
- Semantic search
Limits
- 512 token context only
- No vision or generation
- Requires GPU or CPU for inference
Best for
- Embedding pipelines
- Semantic search engines
- Vector database indexing
Who it’s for. Developers building embedding pipelines or semantic search solutions. The model is suitable for applications that need Chinese language embeddings and can run on CPU or GPU with llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q8_0 | 0.3 GB | 0.9 GB | Fits | Get file → | |
| F16 | 0.7 GB | 1.2 GB | Fits | Get file → | |
| F32 | 1.3 GB | 1.8 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K_M (0.2 GB, 1.5 GB memory) or Q8_0 (0.35 GB, 1.7 GB memory) are suitable. For 4 GB VRAM, Q4_K_M is recommended. For higher accuracy and more memory, use F16 or F32.
What GPU do you need for bge-large-zh-v1.5?
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 F32 (1.3 GB file, about 2.6 GB in use).
Which bge-large-zh-v1.5 quant should you choose?
Q4_K_M is the usual starting point for bge-large-zh-v1.5: it balances file size and quality well. Here it is a 0.2 GB file.
The Q8_0 file is 0.3 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 bge-large-zh-v1.5
How much VRAM does bge-large-zh-v1.5 need?
About 1.5 GB at Q4_K_M with an 8K context window. That is the 0.2 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 bge-large-zh-v1.5 on an 8 GB GPU?
Yes, with F32: the 1.3 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 bge-large-zh-v1.5 GGUF?
It depends on the quant: Q4_K_M is 0.2 GB, Q8_0 is 0.3 GB, F16 is 0.7 GB, F32 is 1.3 GB.
What context length does bge-large-zh-v1.5 support?
The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.1 GB at 512.
Where can I download bge-large-zh-v1.5 GGUF?
The files are on Hugging Face in the CompendiumLabs/bge-large-zh-v1.5-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 bge-large-zh-v1.5 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 bge-large-zh-v1.5 on 8 GB VRAM?
Yes, the Q4_K_M or Q8_0 quantizations fit within 8 GB VRAM with estimated memory usage of 1.5–1.7 GB at 8k context.
Does this model support Chinese text?
Yes, the model is designed for Chinese embeddings and supports Chinese language input.
Is there a license restriction?
The model is released under the MIT license, allowing free use and modification.