mxbai-embed-large-v1
🍞 Looking for a simple end-to-end retrieval solution? Meet Omni, our multimodal and multilingual model. Get in touch for access.
Params
340 M
Context
512
Downloads 30d
4.9 M
Likes
820
Download history
daily snapshots · 10 days5.1 M4.9 M
Jul 28Jul 31Aug 3Aug 6
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| mxbai-embed-large-v1-f16.gguf | GGUF | 0.7 GB | 1.3 GB | ✅ Runs comfortably |
| model.safetensors | f16 | 0.7 GB | 1.3 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- BertModel
- Parameters
- 340 M
- Tensor type
- F16
- Context length
- 512
- Vocabulary
- 30,522
- Layers / heads
- 24 / 16
- Licence
- apache-2.0
- First seen on the Hub
- 2024-03-07
- Training datasets
- undisclosed
- MTEB ArguAna (reported)
- 81.508
- MTEB BIOSSES (reported)
- 87.918268337627
- MTEB ArxivClusteringP2P (reported)
- 48.972945043179
- MTEB ArxivClusteringS2S (reported)
- 42.980710776746
- MTEB BiorxivClusteringP2P (reported)
- 39.917736085828
- MTEB BiorxivClusteringS2S (reported)
- 36.730594774625
- MTEB AskUbuntuDupQuestions (reported)
- 78.235830805083
- MTEB Banking77Classification (reported)
- 87.798793373169
- MTEB CQADupstackAndroidRetrieval (reported)
- 32.746
- MTEB AmazonPolarityClassification (reported)
- 93.829783389729
- MTEB AmazonReviewsClassification (en) (reported)
- 48.741632277516
- MTEB AmazonCounterfactualClassification (en) (reported)
- 68.927365733598
- Added to our catalog
- 2026-07-28
Compare with
Sponsored · GPU cloud
Not enough VRAM?
Spin up a 24 GB L4 instance in 40 seconds. $0.44/hr.