Can the Apple M3 Max (48 GB) run WildGuard 7B?

Yes, but slowly

Slow. At Q8_0 it needs about 11.4 GB of 36.0 GB usable and makes one decision in about 571 ms.

Best quant: Q8_0
Time per decision: 571 ms
Decisions per second: 1.8/s
Input assumed: 512 tokens
Returns: Fixed labels

Best app to run it on the Apple M3 Max (48 GB)

On macOS

Sentence Transformers

Python library · runs on PyTorch (Transformers)

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

Get Sentence Transformers

Docker Model Runner Handy if you already work in Docker.

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 WildGuard 7B

Original weights · Hugging Face

Full-precision files from Ai2, for fine-tuning, vLLM, Transformers.

huggingface.co/allenai/wildguard (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

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

How it’s rated

Quality 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (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 Slow: How well it runs on the Apple M3 Max (48 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.	36.0 / 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.	25.0 / 25
SpeedTime for one decision against a 100 ms target: reading the input plus any tokens the model writes.	6.3 / 15
ClarityHow easy the answer is to use in code: a probability or score earns the most, written feedback before a score the least.	12.0 / 15
Match score	79.3 / 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 Apple M3 Max (48 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q4_K_M`	8.2 GB	36.0 GB	472 ms	Slow	76Great quality (A) · 76 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`	8.9 GB	36.0 GB	494 ms	Slow	77Great quality (A) · 77 of 100: how capable the model is at Q5_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)
`Q6_K`	9.7 GB	36.0 GB	517 ms	Slow	79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q8_0`	11.4 GB	36.0 GB	571 ms	Slow	80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	18.2 GB	36.0 GB	808 ms	Slow	80Great quality (A) · 80 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 and about 6 tokens written. Batching servers process many requests at once.

Other hardware that runs it

80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q8_0 · 92 ms · Runs great
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q8_0 · 84 ms · Runs great
79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q6_K · 115 ms · Runs great
79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q6_K · 117 ms · Runs great
79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Q6_K · 149 ms · Runs well
79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q6_K · 158 ms · Runs well

Quick answers

How much memory does WildGuard 7B need on the M3 Max 48GB?

At Q8_0 it needs about 11.4 GB. The M3 Max 48GB has 36.0 GB usable.

How fast is WildGuard 7B on the M3 Max 48GB?

It makes one decision in about 571 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.