FitMyLLM
mixedbread-ai/Dense

Mmxbai-embed-large-v1

Mixed-bread AI's embedding model, strong on retrieval benchmarks.

embedding
0.335B
Parameters
1K
Context length
1
Benchmarks
6
Quantizations
1.8M
HF downloads
Architecture
Dense
Released
2024-03-07
Layers
24
KV Heads
16
Head Dim
64
Family
embedding

Quantization Options

QuantBitsVRAM @ 512Quality
Q4_K_M4.89
0.7 GB
good
Q5_K_S5.57
0.7 GB
good
Q5_K_M5.7
0.7 GB
good
Q6_K6.56
0.8 GB
excellent
Q8_08.5
0.8 GB
lossless
FP1616
1.2 GB
lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
Ready to run this?Rent by the hour

Rent a GPU and run mxbai-embed-large-v1 now

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (1)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run mxbai-embed-large:335m

Ollama's default build of this model. For Q4_K_M specifically, pick a tag from ollama.com/library/mxbai-embed-large/tags.

Setup guide
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

Find the best GPU for mxbai-embed-large-v1

Build Hardware for mxbai-embed-large-v1

Mixed-bread AI's embedding model, strong on retrieval benchmarks.

Spec sheet

mxbai-embed-large-v1 — 0.335B Dense.

Specifications
Parameters
0.335B
Architecture
Dense Transformer
Context Length
1K tokens
Capabilities
embedding
Release Date
2024-03-07
Provider
mixedbread-ai
Family
embedding
VRAM requirements
QuantBPWVRAMQuality
Q4_K_M4.890.7 GB94%
Q5_K_S5.570.7 GB96%
Q5_K_M5.70.7 GB96%
Q6_K6.560.8 GB97%
Q8_08.50.8 GB100%
FP16161.2 GB100%
Benchmark scores
MTEB Retrieval55.4
Run command

Run mxbai-embed-large-v1 locally with Ollama — needs 0.7 GB VRAM at Q4_K_M:

$ollama run mxbai-embed-large:335m
Compatible GPUs
30 @ Q4_K_M