Olmo 3.1 32B Instruct on Apple M5 Pro (24 GB)

Can the Apple M5 Pro (24 GB) run Olmo 3.1 32B Instruct?

Yes, it runs well (tight fit)

Runs well (tight fit). At Q2_K it needs about 15.5 GB of 16.1 GB usable, with an estimated speed of 16.5 tok/s.

Best quant: Q2_K
Generation speed: 16.5 tok/s
Prompt processing: 181 tok/s
First token (1K prompt): 5.7 s
Largest safe context: 14K

Best app to run it on the Apple M5 Pro (24 GB)

On macOS

LM Studio

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

Runs the MLX build, typically up to 10% faster than GGUF for a model with 32.2B active parameters on Apple silicon.
Point-and-click: search, download and chat in one window.

Open Olmo 3.1 32B 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 3.1 32B Instruct

Recommended for the Apple M5 Pro (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 olmo-3.1:32b-instruct

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/unsloth/Olmo-3.1-32B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Olmo-3.1-32B-Instruct-GGUF:Q2_K

Original weights · Hugging Face

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

huggingface.co/allenai/Olmo-3.1-32B-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 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 71/100 (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 welltight fit: How well it runs on the Apple M5 Pro (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.	22.7 / 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.	24.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	9.6 / 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	71.3 / 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 M5 Pro (24 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	15.5 GB	16.1 GB	16.5 tok/s	Runs welltight fit	50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	18.4 GB	16.1 GB	11.1 tok/s	Slowfar over GPU memory limit	60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	22.3 GB	16.1 GB	—	Won't run	68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	25.5 GB	16.1 GB	—	Won't run	69Good quality (B) · 69 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	29.1 GB	16.1 GB	—	Won't run	71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	36.8 GB	16.1 GB	—	Won't run	72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	67.1 GB	16.1 GB	—	Won't run	72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (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

69Good quality (B) · 69 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q5_K_M · 56.4 tok/s · Runs great
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q4_K_M · 38.4 tok/s · Runs well (tight fit)
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q4_K_M · 35.6 tok/s · Runs well (tight fit)
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q4_K_M · 31.5 tok/s · Runs well (tight fit)
71Great quality (A) · 71 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. NVIDIA RTX PRO 6000 Blackwell Q6_K · 47.4 tok/s · Runs great
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q4_K_M · 17.9 tok/s · Runs well

Quick answers

How much memory does Olmo 3.1 32B Instruct need on the M5 Pro 24GB?

At Q2_K it needs about 15.5 GB. The M5 Pro 24GB has 16.1 GB usable.

How fast is Olmo 3.1 32B Instruct on the M5 Pro 24GB?

About 16.5 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Olmo 3.1 32B Instruct should I use on the M5 Pro 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.