ms-marco MiniLM L6 v2 on UDOO BOLT V8 (8 GB)

Can the UDOO BOLT V8 (8 GB) run ms-marco MiniLM L6 v2?

Yes, it runs great

Runs great. At F16 it needs about 0.7 GB of 4.0 GB usable and makes one decision in about 15 ms.

Best precision: F16
Time per decision: 15 ms
Decisions per second: 69/s
Input assumed: 512 tokens
Returns: Probability or score

Best app to run it on the UDOO BOLT V8 (8 GB)

On Windows

LocalAI

Inference server · runs on llama.cpp, rerankers (Python), Transformers

One OpenAI-compatible server for GGUF guard models and rerankers together.
On Windows it runs through WSL2.

Get LocalAI

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

On Linux

LocalAI

Inference server · runs on llama.cpp, rerankers (Python), Transformers

One OpenAI-compatible server for GGUF guard models and rerankers together.

Get LocalAI

Text Embeddings Inference Can only use the CPU on this hardware, so it will be slow.
Infinity 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 ms-marco MiniLM L6 v2

Original weights · Hugging Face

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

huggingface.co/cross-encoder/ms-marco-MiniLM-L6-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 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at F16, 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 Runs great: How well it runs on the UDOO BOLT V8 (8 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.	23.4 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	25.0 / 25
SpeedTime for one decision against a 100 ms target: reading the input plus any tokens the model writes.	15.0 / 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	78.4 / 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 UDOO BOLT V8 (8 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q8_0`	0.6 GB	4.0 GB	13 ms	Runs great	52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	0.7 GB	4.0 GB	15 ms	Runs great	52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (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. Batching servers process many requests at once.

Other hardware that runs it

52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX F16 · 4.2 ms · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT F16 · 4.2 ms · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. AMD Ryzen AI Max+ 395 (128 GB) F16 · 4.4 ms · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 (16 GB) F16 · 13 ms · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 Max (64 GB) F16 · 6.3 ms · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) F16 · 4.9 ms · Runs great

Quick answers

How much memory does ms-marco MiniLM L6 v2 need on the UDOO BOLT V8 8GB?

At F16 it needs about 0.7 GB. The UDOO BOLT V8 8GB has 4.0 GB usable.

How fast is ms-marco MiniLM L6 v2 on the UDOO BOLT V8 8GB?

It makes one decision in about 15 ms at F16, 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.