Mixedbread AI
mxbai Embed Large (0.33500000834465027B parameters) requires approximately 4.0 GB of VRAM with F16 quantization. For the best balance of quality and speed, we recommend hardware with at least 5 GB of VRAM.
Get started
— copy & paste to run locallyCopy-paste commands to run mxbai Embed Large on your machine.
Run
ollama run mxbai-embed-largeQuick specs
About this model
Quick picks
Best hardware
Run this model
Quantization options
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 0.1 GB | Low | — |
Q3_K_S | 3 | 0.2 GB | Low | — |
NVFP4 | 4 | 0.2 GB | Medium | — |
Q4_K_M | 4 | 0.2 GB | Medium | — |
Q5_K_M | 5 | 0.2 GB | High | — |
Q6_K | 6 | 0.3 GB | High | — |
Q8_0 | 8 | 0.4 GB | Very High | — |
F16 | 16 | 0.7 GB | Maximum | — |
Hardware compatibility
Computing compatibility...
Memory breakdown
Frequently asked questions
mxbai Embed Large (0.33500000834465027B parameters) requires approximately 4.0 GB of VRAM with F16 quantization. Lower quantizations like Q4_K_M use less memory but may reduce quality.
Yes, Intel Arc A380 6GB can run mxbai Embed Large with a compatibility score of 81/100. It provides 6 GB of memory and achieves approximately 4.7 tokens per second.
The recommended quantization for mxbai Embed Large is F16, which offers the best balance between model quality and memory efficiency. Higher quantizations preserve more quality but require more VRAM.
The top recommended hardware for mxbai Embed Large: Intel Arc A370M 4GB (score: 82/100), RTX 2060 6GB (score: 81/100), RTX 4050 Laptop 6GB (score: 81/100). These provide the best combination of memory, bandwidth, and compute for running this model locally.
Yes, mxbai Embed Large is well-suited for embedding as well as rag. It was designed with these use cases in mind.
See also
