mxbai-rerank-large v2 on UP Squared Pro 7000 (4 GB)

Can the UP Squared Pro 7000 (4 GB) run mxbai-rerank-large v2?

Yes, but slowly (tight fit)

Slow (tight fit). At Q5_K_M it needs about 1.9 GB of 2.0 GB usable and makes one decision in about 1.2 s.

Best quant: Q5_K_M
Time per decision: 1.2 s
Decisions per second: 0.9/s
Input assumed: 512 tokens
Returns: Probability or score

Best app to run it on the UP Squared Pro 7000 (4 GB)

On Windows

vLLM

Inference server · runs on vLLM

Serves the scoring head directly (rerank, classify or reward) with batching.
On Windows it runs through WSL2.

vllm serve mixedbread-ai/mxbai-rerank-large-v2

Sentence Transformers Can only use the CPU on this hardware, so it will be slow.

On Linux

vLLM

Inference server · runs on vLLM

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

vllm serve mixedbread-ai/mxbai-rerank-large-v2

Sentence Transformers Can only use the CPU on this hardware, so it will be slow.

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download mxbai-rerank-large v2

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 2 hours ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 79Great quality (A) · 79 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q5_K_M, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Slowtight fit: How well it runs on the UP Squared Pro 7000 (4 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

PrecisionEditorial precision tier from the model’s published benchmarks, scaled by the quantization or precision used.	35.8 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	24.0 / 25
SpeedTime for one decision against a 100 ms target: reading the input plus any tokens the model writes.	4.4 / 15
ClarityHow easy the answer is to use in code: a probability or score earns the most, written feedback before a score the least.	15.0 / 15
Match score	79.2 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the UP Squared Pro 7000 (4 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q4_K_M`	1.8 GB	2.0 GB	1.2 s	Slowtight fit	77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q5_K_M`	1.9 GB	2.0 GB	1.2 s	Slowtight fit	79Great quality (A) · 79 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q6_K`	2.1 GB	2.0 GB	1.2 s	Slowover GPU memory limit	81Great quality (A) · 81 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q8_0`	2.5 GB	2.0 GB	1.2 s	Slowfar over GPU memory limit	82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	3.9 GB	2.0 GB	—	Won't run	82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Times are for one request with a 512-token input and about 1 tokens written. Batching servers process many requests at once.

Other hardware that runs it

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 · 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 · 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 · 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 · 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 · 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 · 56 ms · Runs great

Quick answers

How much memory does mxbai-rerank-large v2 need on the UP Squared Pro 7000 4GB?

At Q5_K_M it needs about 1.9 GB. The UP Squared Pro 7000 4GB has 2.0 GB usable.

How fast is mxbai-rerank-large v2 on the UP Squared Pro 7000 4GB?

It makes one decision in about 1.2 s at Q5_K_M, an estimate from the hardware and the size of the model.

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.