bge-large-en-v1.5
Q4 GGUF download: mradermacher/bge-large-en-v1.5-GGUF - 0.22 GB on disk, read 2026-11-16. VRAM figures above are estimates; this is the actual file size.
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve BAAI/bge-large-en-v1.5New to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
bge-large-en-v1.5 is an open-weight text embedding model published by BAAI on Hugging Face in September 2023, with 340M parameters under the mit license.
Among the 19 text embedding models in this directory it ranks 10th by monthly Hugging Face downloads, and 8 of the others are larger.
HardwareLink to this section
Unquantized FP16 weights take about 1 GB; 8-bit brings that to ~1 GB and 4-bit (Q4_K_M) to ~1 GB, before activations and any context or image buffers. At this size it runs on almost any recent GPU, on Apple Silicon, and usable on a modern CPU. Check exact numbers for your card with the VRAM calculator.
Similar text embedding modelsLink to this section
- Qwen3-Embedding-0.6B - 600M, 7,566,974 downloads/month
- multilingual-e5-large - 560M, 7,318,858 downloads/month
- multilingual-e5-base - 280M, 4,651,836 downloads/month
- harrier-oss-v1-0.6b - 600M, 234,641 downloads/month
- voyage-4-nano - 350M, 156,246 downloads/month
PopularityLink to this section
bge-large-en-v1.5 was downloaded 6,814,594 times on Hugging Face in the last month (181,894,455 all-time) and has 787 likes.
Run it locallyLink to this section
Weights and usage instructions are on the BAAI/bge-large-en-v1.5 model card; it loads with sentence-transformers.
Local runtimes that fit this model:
- transformers - the reference Python library most model cards target
PaperLink to this section
From the community
What users are saying
“Internal model structure here: https://app.svetoviz.com?bucket=baai-bge-large-en-v1-5”
“Hello, just wondering. We dont need instruction query though correct? I am using sentencetransformers, and this is important. I have Long query, and my passages are short, Imagine a customer complaint, and then a simple short comment that is picked that best matches the Long user query.”
“Sorry for the late reply. I missed this comment. The difference between the HuggingFaceBgeEmbeddings and HuggingFaceEmbeddings is whether instruction is added. Maybe the instruction will drop the performance in your cases. More information about the evaluation method provided will be helpful in analyzing this problem.”
Frequently asked
Quick answers to common questions
How much VRAM does bge-large-en-v1.5 need?
bge-large-en-v1.5 with 340M parameters needs approximately 1 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is bge-large-en-v1.5 better than other BAAI models?
bge-large-en-v1.5 has 340M parameters - a strong choice for embeddings.
What license is bge-large-en-v1.5 under?
bge-large-en-v1.5 is released under the mit license, making it suitable for most commercial and personal projects.
What hardware runs bge-large-en-v1.5 well?
With 340M parameters, bge-large-en-v1.5 is small enough for most consumer GPUs, Apple Silicon Macs, and many CPUs. Check our hardware directory for specific recommendations.
What is the best quantization for bge-large-en-v1.5?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~1 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
What models compete with bge-large-en-v1.5?
bge-large-en-v1.5 competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec