mixedbread-ai models

2 mixedbread-ai models from mixedbread-ai on Hugging Face, from 494M to 1.5B parameters, published by mixedbread-ai in F16, with a 32K-token context. The smallest official model, mxbai-rerank-base-v2, needs about 1.1 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.

Pick a size

One row per official mixedbread-ai size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.

ModelParametersNative VRAMFP8 VRAMINT4 VRAMLive GPU fit (native)Est. $/hrKV cache at 32K
mxbai-rerank-base-v2494M1.1 GB0.6 GB0.3 GBRTX 3070$0.088/hr0.38 GB
mxbai-rerank-large-v21.5B3.5 GB1.7 GB0.9 GBRTX 3070$0.088/hr0.88 GB

VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.

Official models (2)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
mxbai-rerank-base-v2494MF161.1 GBRTX 3070$0.088/hr
mxbai-rerank-large-v21.5BF163.5 GBRTX 3070$0.088/hr

VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.