Run mixedbread-ai/mxbai-embed-large-v1 locally
mixedbread-ai/mxbai-embed-large-v1 is a compact language model with 0.34 billion parameters, built on the bert architecture. It is released under the apache-2.0 license and has been downloaded 5,778,237 times.
To run mixedbread-ai/mxbai-embed-large-v1 locally at a 4,096-token context, its quantized versions need between 1.8 GB (F16, lowest quality) and 1.8 GB (F16, highest quality) of memory, weights plus KV cache and a system margin included.
For most users the best balance is F16, needing about 1.8 GB. That means mixedbread-ai/mxbai-embed-large-v1 fits entirely in the VRAM of a 6 GB GPU or larger, running fully on the GPU.
All quantizations
| Quant. | Bits | Quality | Weights | KV | Total | Speed~ | Verdict |
|---|---|---|---|---|---|---|---|
| F16 | 15.98 | Excellent | 0.62 GB | 0.38 GB | 1.8 GB | 641.4 t/s | Fits in VRAM |
KV cache computed from the model's exact architecture. Speed is a rough estimate bounded by memory bandwidth.
Frequently asked questions
How much VRAM do you need to run mixedbread-ai/mxbai-embed-large-v1?
You need about 1.8 GB of VRAM to run mixedbread-ai/mxbai-embed-large-v1 entirely on the GPU using the F16 quantization (at a 4,096-token context). Smaller quantizations lower the requirement at the cost of quality.
Can I run mixedbread-ai/mxbai-embed-large-v1 on an 8 GB GPU?
Yes. With 8 GB of VRAM you can run mixedbread-ai/mxbai-embed-large-v1 fully on the GPU using F16 (about 1.8 GB).
Can I run mixedbread-ai/mxbai-embed-large-v1 on a 16 GB GPU?
Yes. With 16 GB of VRAM you can run mixedbread-ai/mxbai-embed-large-v1 fully on the GPU using F16 (about 1.8 GB).
Can I run mixedbread-ai/mxbai-embed-large-v1 on a 24 GB GPU?
Yes. With 24 GB of VRAM you can run mixedbread-ai/mxbai-embed-large-v1 fully on the GPU using F16 (about 1.8 GB).
What is the best quantization for mixedbread-ai/mxbai-embed-large-v1?
If memory allows, higher bits-per-weight means better quality. A common sweet spot is a Q4_K_M or Q5_K_M quantization, which keeps most of the quality while roughly halving the memory versus 8-bit. Pick the highest quantization that still fits in your VRAM.