on

Can the Apple M2 Ultra (192 GB) run DeBERTa v3 Large Zero-shot v2.0?

72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs great

Runs great. At F16 it needs about 1.6 GB of 144 GB usable and makes one decision in about 12 ms.

Best precision
F16
Time per decision
12 ms
Decisions per second
81/s
Input assumed
256 tokens
Returns
Probability or score

Best app to run it on the Apple M2 Ultra (192 GB)

On macOS

Infinity

Inference server · runs on PyTorch, ONNX, CTranslate2

  • Local API for rerankers and classifiers, including models TEI does not support.
infinity_emb v2 --model-id MoritzLaurer/deberta-v3-large-zeroshot-v2.0
  • Sentence Transformers A few lines of Python with Transformers or Sentence Transformers; easiest for scripts and notebooks.

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 DeBERTa v3 Large Zero-shot v2.0

Original weights · Hugging Face

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

huggingface.co/MoritzLaurer/deberta-v3-large-zeroshot-v2.0 (opens in a new tab)

No sign-in needed.

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (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: S 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great
How well it runs on the Apple M2 Ultra (192 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.32.4 / 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 score87.4 / 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 M2 Ultra (192 GB)

Quant Memory needed Available Time per decision Runs Quality Download
Q8_0 1.2 GB 144 GB 11 ms Runs great 72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
F16 1.6 GB 144 GB 12 ms Runs great 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Original weights (opens in a new tab)

Times are for one request with a 256-token input. Batching servers process many requests at once.

Other hardware that runs it

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.