OLMoE 1B-7B Instruct on Apple M3 Ultra (256 GB)

Can the Apple M3 Ultra (256 GB) run OLMoE 1B-7B Instruct?

Yes, it runs great

Runs great. At F16 it needs about 30.3 GB of 192 GB usable, with an estimated speed of 92.8 tok/s.

Best quant: F16
Generation speed: 92.8 tok/s
Prompt processing: 13,545 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 4K

Best app to run it on the Apple M3 Ultra (256 GB)

On macOS

LM Studio

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

Runs the MLX build, typically 35–90% faster than GGUF for a model with 1.3B active parameters on Apple silicon.
Point-and-click: search, download and chat in one window.

Open OLMoE 1B-7B Instruct in LM Studio

MLX LM Runs the MLX build, typically 35–90% faster than GGUF for a model with 1.3B active parameters on Apple silicon.
Unsloth Desktop Runs the MLX build, typically 35–90% faster than GGUF for a model with 1.3B active parameters on Apple silicon.

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 OLMoE 1B-7B Instruct

Recommended for the Apple M3 Ultra (256 GB): F16. 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 F16 file (opens in a new tab)

huggingface.co/allenai/OLMoE-1B-7B-0125-Instruct-GGUF (opens in a new tab)

ollama run hf.co/allenai/OLMoE-1B-7B-0125-Instruct-GGUF:F16

Original weights · Hugging Face

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

huggingface.co/allenai/OLMoE-1B-7B-0125-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/OLMoE (opens in a new tab)

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

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

How it’s rated

Quality 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (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: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great: How well it runs on the Apple M3 Ultra (256 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.	11.7 / 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.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	3.6 / 15
Match score	55.3 / 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 Ultra (256 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	19.3 GB	192 GB	248 tok/s	Runs great	18Basic quality (D) · 18 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	19.9 GB	192 GB	227 tok/s	Runs great	21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	20.7 GB	192 GB	205 tok/s	Runs great	24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	21.4 GB	192 GB	188 tok/s	Runs great	25Basic quality (D) · 25 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	22.2 GB	192 GB	173 tok/s	Runs great	25Basic quality (D) · 25 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	23.8 GB	192 GB	148 tok/s	Runs great	26Basic quality (D) · 26 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.	GGUF (opens in a new tab)
`F16`	30.3 GB	192 GB	92.8 tok/s	Runs great	26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (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

26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX F16 · 102 tok/s · Runs great
26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 Q8_0 · 102 tok/s · Runs great
26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GB Q8_0 · 104 tok/s · Runs great
26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 F16 · 109 tok/s · Runs great
26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER Q8_0 · 126 tok/s · Runs great
26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 F16 · 113 tok/s · Runs great

Quick answers

How much memory does OLMoE 1B-7B Instruct need on the M3 Ultra 256GB?

At F16 it needs about 30.3 GB. The M3 Ultra 256GB has 192 GB usable.

How fast is OLMoE 1B-7B Instruct on the M3 Ultra 256GB?

About 92.8 tok/s at F16, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of OLMoE 1B-7B Instruct should I use on the M3 Ultra 256GB?

F16. 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.