MxBai Embed Large

What MxBai Embed Large is for

MxBai Embed Large is an embedding model, not a chat model: it turns text into vectors so a retrieval system can find the passages worth showing a language model. Mixedbread AI released it in 2024-04 under Apache 2.0, with a single 335M size and 512 of context. It is the piece you run alongside a generator in a local RAG stack, and the catalogue records its strength as high-quality English embeddings.

Sizes and memory

Our catalogue carries no per-size memory breakdown for MxBai Embed Large, and at 335M it does not need one: the record puts its floor at CPU inference, with 1 GB named as a comfortable allocation if you do have a card. That is the whole memory story for a model this small.

Hardware that runs MxBai Embed Large

MxBai Embed Large needs no GPU. Its recorded floor is CPU inference, with 1 GB recommended if you do have a card to put it on — which for an embedding model usually means keeping it resident next to a generator rather than needing the memory for itself. Any entry in our hardware guide runs it, and so does a machine with none of them.

What people use it for

The catalogue lists 3 recorded uses for MxBai Embed Large: RAG, retrieval, semantic search. It is tagged embedding, retrieval, RAG.

Where MxBai Embed Large sits in the MxBai family

MxBai Embed Large is the only MxBai entry in our catalogue, so there is no in-family alternative to weigh it against; the comparison to make is against the models listed at the foot of this page.

The Apache 2.0 licence puts no usage ceiling on it, which matters if the thing you are building has users. That is the practical difference between this and a vendor community licence.

Context window: 512

512 tokens is a short window by 2026 standards — on the order of a few hundred words at the usual three-quarters-of-a-word-per-token ratio. That is one conversation turn with a document, not a session with a codebase. Anything longer has to be retrieved and injected rather than held.

How to run MxBai Embed Large locally

Our catalogue does not record registry tags, so look the current tag up in the Ollama library or on Hugging Face before pasting these. The commands below are the shape of the workflow, not a copy-and-paste recipe.

Option 1: Ollama (simplest)

# find the tag for MxBai Embed Large at ollama.com/library
ollama run <tag>

Option 2: Mullama (production)

mullama pull <tag>
mullama run <tag>

Option 3: llama.cpp (CLI)

# download a GGUF from Hugging Face, searching for "MxBai Embed Large GGUF"
./llama-cli -m model.Q4_K_M.gguf -p "Hello, AI!"

Option 4: Python with Mullama or llama-cpp-python

from mullama import Model, Context
model = Model.load("model.Q4_K_M.gguf", n_gpu_layers=99)
ctx = Context(model, n_ctx=4096)
print(ctx.generate("Hello, AI!", 256))

Sources

Model record from src/data/models.json (2026-06-29); card capacities from src/data/gpus.json (2026-06-29). Upstream: Curated from ollama.com/library + community benchmarks + paperswithcode + huggingface.