on

Can the Apple M3 Ultra (96 GB) run Apertus v1.5 70B?

62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs well

Runs well. At Q4_K_M it needs about 53.0 GB of 72.0 GB usable, with an estimated speed of 12.0 tok/s.

Best quant
Q4_K_M
Generation speed
12.0 tok/s
Prompt processing
245 tok/s
First token (1K prompt)
4.2 s
Largest safe context
64K

Best app to run it on the Apple M3 Ultra (96 GB)

On macOS

Docker Model Runner

Command line + local API · runs on llama.cpp, vLLM

  • Handy if you already work in Docker.
docker model run hf.co/swiss-ai/Apertus-v1.5-70B

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 Apertus v1.5 70B

Original weights · Hugging Face

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

huggingface.co/swiss-ai/Apertus-v1.5-70B (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 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q4_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 Runs well
How well it runs on the Apple M3 Ultra (96 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.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.28.2 / 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
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.8.2 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.15.0 / 15
Match score76.4 / 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 Apple M3 Ultra (96 GB)

Quant Memory needed Available Speed Runs Quality Download
Q2_K 37.8 GB 72.0 GB 19.7 tok/s Runs well 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q3_K_M 44.3 GB 72.0 GB 15.5 tok/s Runs well 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q4_K_M 53.0 GB 72.0 GB 12.0 tok/s Runs well 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q5_K_M 60.2 GB 72.0 GB 9.9 tok/s Slow 64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q6_K 68.1 GB 72.0 GB 8.3 tok/s Slowtight fit 65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q8_0 85.4 GB 72.0 GB 5.2 tok/s Slowfar over GPU memory limit 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
F16 153 GB 72.0 GB — Won't run 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

Quick answers

How much memory does Apertus v1.5 70B need on the M3 Ultra 96GB?

At Q4_K_M it needs about 53.0 GB. The M3 Ultra 96GB has 72.0 GB usable.

How fast is Apertus v1.5 70B on the M3 Ultra 96GB?

About 12.0 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Apertus v1.5 70B should I use on the M3 Ultra 96GB?

Q4_K_M. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

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.

Was this page helpful?