Llama Prompt Guard 2 86M on UP Squared Pro 7000 (16 GB)

Can the UP Squared Pro 7000 (16 GB) run Llama Prompt Guard 2 86M?

Yes, it runs well

Runs well. At Q8_0 it needs about 1.0 GB of 8.0 GB usable and makes one decision in about 225 ms.

Best precision: Q8_0
Time per decision: 225 ms
Decisions per second: 4.4/s
Input assumed: 512 tokens
Returns: Probability or score

Best app to run it on the UP Squared Pro 7000 (16 GB)

On Windows

Sentence Transformers

Python library · runs on PyTorch (Transformers)

Can only use the CPU on this hardware, so it will be slow.
A few lines of Python with Transformers or Sentence Transformers; easiest for scripts and notebooks.

python -c "from transformers import pipeline; print(pipeline('text-classification', model='meta-llama/Llama-Prompt-Guard-2-86M')('text'))"

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

On Linux

Infinity

Inference server · runs on PyTorch, ONNX, CTranslate2

Can only use the CPU on this hardware, so it will be slow.
Local API for rerankers and classifiers, including models TEI does not support.

infinity_emb v2 --model-id meta-llama/Llama-Prompt-Guard-2-86M

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 Llama Prompt Guard 2 86M

Original weights · Hugging Face

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

huggingface.co/meta-llama/Llama-Prompt-Guard-2-86M (opens in a new tab)

Free Hugging Face account needed: request access on the model page, and Meta approves it (usually within minutes to a few hours).

Links checked 5 hours ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q8_0, 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 well: How well it runs on the UP Squared Pro 7000 (16 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.	34.2 / 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.	10.0 / 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	84.2 / 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 (16 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q8_0`	1.0 GB	8.0 GB	225 ms	Runs well	76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	1.2 GB	8.0 GB	259 ms	Runs well	76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 83/100 (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

76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX F16 · 6.4 ms · Runs great
76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT F16 · 7.0 ms · Runs great
76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. AMD Ryzen AI Max+ 395 (128 GB) F16 · 8.9 ms · Runs great
76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 Max (64 GB) F16 · 32 ms · Runs great
76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) F16 · 15 ms · Runs great
76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (256 GB) F16 · 14 ms · Runs great

Quick answers

How much memory does Llama Prompt Guard 2 86M need on the UP Squared Pro 7000 16GB?

At Q8_0 it needs about 1.0 GB. The UP Squared Pro 7000 16GB has 8.0 GB usable.

How fast is Llama Prompt Guard 2 86M on the UP Squared Pro 7000 16GB?

It makes one decision in about 225 ms at Q8_0, 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.