Can the Apple M3 (24 GB) run OLMo 2 13B Instruct?

Yes, it runs well

Runs well. At Q2_K it needs about 10.7 GB of 16.1 GB usable, with an estimated speed of 12.7 tok/s.

Best quant: Q2_K
Generation speed: 12.7 tok/s
Prompt processing: 185 tok/s
First token (1K prompt): 5.5 s
Largest safe context: 4K

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

On macOS

LM Studio

Desktop app · runs on llama.cpp, MLX · use the MLX build

Runs the MLX build, typically 10–20% faster than GGUF for a model with 13.7B active parameters on Apple silicon.
Point-and-click: search, download and chat in one window.

Open OLMo 2 13B Instruct in LM Studio

Ollama One command with Ollama’s own build of this model.
llama.cpp Usually the first to support new model architectures.

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 OLMo 2 13B Instruct

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

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run olmo2:13b

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/allenai/OLMo-2-1124-13B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/allenai/OLMo-2-1124-13B-Instruct-GGUF:Q2_K

Original weights · Hugging Face

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

huggingface.co/allenai/OLMo-2-1124-13B-Instruct (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Ai2. The weights themselves download from Hugging Face.

github.com/allenai/OLMo (opens in a new tab)

git clone https://github.com/allenai/OLMo

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

How it’s rated

Quality 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (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.	13.9 / 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.	8.4 / 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 score	62.3 / 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 (24 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	10.7 GB	16.1 GB	12.7 tok/s	Runs well	30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	12.0 GB	16.1 GB	10.0 tok/s	Slow	36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	13.6 GB	16.1 GB	7.7 tok/s	Slow	41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	15.0 GB	16.1 GB	6.4 tok/s	Slowtight fit	42Fair quality (C) · 42 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	16.5 GB	16.1 GB	4.5 tok/s	Slowover GPU memory limit	43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	19.8 GB	16.1 GB	3.3 tok/s	Slowfar over GPU memory limit	44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	32.7 GB	16.1 GB	—	Won't run	44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 5/100 (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 4K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q8_0 · 42.6 tok/s · Runs great
44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q8_0 · 45.9 tok/s · Runs great
43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q6_K · 51.3 tok/s · Runs great
44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q8_0 · 81.6 tok/s · Runs great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q4_K_M · 49.3 tok/s · Runs great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q4_K_M · 60.1 tok/s · Runs great

Quick answers

How much memory does OLMo 2 13B Instruct need on the M3 24GB?

At Q2_K it needs about 10.7 GB. The M3 24GB has 16.1 GB usable.

How fast is OLMo 2 13B Instruct on the M3 24GB?

About 12.7 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of OLMo 2 13B Instruct 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.