Decision models · Mixedbread

mxbai-rerank-large v2

Name: mxbai-rerank-large v2
Author: Mixedbread

Task: Reranking search results
Returns: Probability or score
Precision tier: 82 / 100
Size: 1.5B
Max input: 32K tokens
License: apache-2.0
Released: 2025-03

What it decides

Returns: A relevance score for each query and document pair.
Checks: Query and document pairs, code, JSON
Languages: 100+ languages
Precision: 82 / 100 · Mixedbread reports BEIR nDCG@10 57.5 for large v2.
Clarity: Probability or score (15 of 15 clarity points)
How it runs: Scores query and document pairs · a small language model, so it runs in the same apps as LLMs.
License: apache-2.0 (Open (Apache, MIT))

Source: model card on Hugging Face (opens in a new tab) · How decision models are rated

How to run it

Original weights · Hugging Face

Full-precision files from Mixedbread, for Transformers, Sentence Transformers, Text Embeddings Inference, Infinity or vLLM.

huggingface.co/mixedbread-ai/mxbai-rerank-large-v2 (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

Apps that run mxbai-rerank-large v2

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or Mac in the Model Finder for an exact answer.

Mac (Apple silicon)

Sentence Transformers

A few lines of Python with Transformers or Sentence Transformers; easiest for scripts and notebooks.

Windows PC, NVIDIA GPU

Sentence Transformers

A few lines of Python with Transformers or Sentence Transformers; easiest for scripts and notebooks.

Also good: vLLM

Windows PC, AMD Radeon

Sentence Transformers

A few lines of Python with Transformers or Sentence Transformers; easiest for scripts and notebooks.

Also good: vLLM

Linux, NVIDIA GPU

vLLM

Serves the scoring head directly (rerank, classify or reward) with batching.

Also good: Sentence Transformers

Linux server, 80 GB+ GPUs

vLLM

Serves the scoring head directly (rerank, classify or reward) with batching.

Also good: Sentence Transformers

App	Type	Opens it as	Systems	Engine	Start
vLLM	Server	Original weights	WSLWindowsLinux	vLLM	`vllm serve mixedbread-ai/mxbai-rerank-large-v2`
Sentence Transformers	Library	Original weights	macOSWindowsLinux	PyTorch	Get Sentence Transformers

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory and speed

Each quantization on an NVIDIA GeForce RTX 4090, for one decision on a 512-token input. The best hardware table below covers other GPUs and Macs.

Format	Memory needed	Time per decision	Decisions per second	Quality	Download
`Q4_K_M`	1.6 GB	19 ms	54/s	77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q5_K_M`	1.8 GB	19 ms	53/s	79Great quality (A) · 79 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q6_K`	1.9 GB	19 ms	52/s	81Great quality (A) · 81 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q8_0`	2.3 GB	20 ms	51/s	82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	3.7 GB	23 ms	44/s	82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

One request at a time. Servers that batch (Text Embeddings Inference, vLLM, Infinity) handle many more decisions per second.

Best hardware for mxbai-rerank-large v2

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at Q8_0.

Quality	Hardware	Quant	Memory	Time per decision	Runs
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 7900 XTX	`F16`	4.9 GB / 24.0 GB	21 ms	Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 9070 XT	`F16`	4.5 GB / 16.0 GB	27 ms	Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	AMD Ryzen AI Max+ 395 (128 GB)	`F16`	11.4 GB / 96.0 GB	50 ms	Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	Apple M2 Ultra (192 GB)	`F16`	15.3 GB / 144 GB	59 ms	Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	Apple M3 Ultra (256 GB)	`F16`	19.1 GB / 192 GB	56 ms	Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	Apple M3 Ultra (512 GB)	`F16`	34.5 GB / 384 GB	56 ms	Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	Apple M4 Max (128 GB)	`F16`	11.4 GB / 96.0 GB	84 ms	Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	Apple M4 Max (64 GB)	`F16`	7.6 GB / 48.0 GB	84 ms	Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	Intel Arc B580	`F16`	4.3 GB / 12.0 GB	72 ms	Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GB10 (128 GB)	`F16`	13.0 GB / 115 GB	59 ms	Runs great

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.