on

Can the Apple M3 (24 GB) run Apriel Nemotron 15B Thinker?

46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs well

Runs well. At Q2_K it needs about 9.6 GB of 16.1 GB usable, with an estimated speed of 11.6 tok/s.

Best quant
Q2_K
Generation speed
11.6 tok/s
Prompt processing
170 tok/s
First token (1K prompt)
6.0 s
Largest safe context
39K

Best app to run it on the Apple M3 (24 GB)

On macOS

LM Studio

Desktop app · runs on llama.cpp, MLX

  • Point-and-click: search, download and chat in one window.

Open Apriel Nemotron 15B Thinker in LM Studio

  • llama.cpp Usually the first to support new model architectures.
  • Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

Want an agent? Apriel Nemotron 15B Thinker supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

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 Apriel Nemotron 15B Thinker

Recommended for the Apple M3 (24 GB): Q2_K. Every other quantization has its own download link in the table below.

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q2_K file (opens in a new tab)

huggingface.co/bartowski/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF (opens in a new tab)

ollama run hf.co/bartowski/ServiceNow-AI_Apriel-Nemotron-15b-Thinker-GGUF:Q2_K

Original weights · Hugging Face

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

huggingface.co/ServiceNow-AI/Apriel-Nemotron-15b-Thinker (opens in a new tab)

No sign-in needed.

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

How it’s rated

Quality 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q2_K, 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 (24 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.20.8 / 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.8.1 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.13.7 / 15
Match score67.6 / 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 (24 GB)

Quant Memory needed Available Speed Runs Quality Download
Q2_K 9.6 GB 16.1 GB 11.6 tok/s Runs well 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q3_K_M 10.9 GB 16.1 GB 9.1 tok/s Slow 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q4_K_M 12.7 GB 16.1 GB 7.1 tok/s Slow 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q5_K_M 14.2 GB 16.1 GB 5.8 tok/s Slowtight fit 64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q6_K 15.8 GB 16.1 GB 4.9 tok/s Slowtight fit 65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q8_0 19.4 GB 16.1 GB 3.1 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 52/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
F16 33.5 GB 16.1 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. GGUF (opens in a new tab) 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 Apriel Nemotron 15B Thinker need on the M3 24GB?

At Q2_K it needs about 9.6 GB. The M3 24GB has 16.1 GB usable.

How fast is Apriel Nemotron 15B Thinker on the M3 24GB?

About 11.6 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Apriel Nemotron 15B Thinker should I use on the M3 24GB?

Q2_K. 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?