StableLM 2 Zephyr 1.6B on Apple M5 Ultra (256 GB)

Can the Apple M5 Ultra (256 GB) run StableLM 2 Zephyr 1.6B?

Yes, it runs great

Runs great. At F16 it needs about 20.0 GB of 192 GB usable, with an estimated speed of 181 tok/s.

Best quant: F16
Generation speed: 181 tok/s
Prompt processing: 14,252 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 4K

Best app to run it on the Apple M5 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 1.6B active parameters on Apple silicon.
Point-and-click: search, download and chat in one window.

Open StableLM 2 Zephyr 1.6B in LM Studio

MLX LM Runs the MLX build, typically 35–90% faster than GGUF for a model with 1.6B active parameters on Apple silicon.
Ollama One command with Ollama’s own build of this model.

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 StableLM 2 Zephyr 1.6B

Recommended for the Apple M5 Ultra (256 GB): F16. 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 stablelm2:1.6b-zephyr-fp16

Quantized files · GGUF

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

huggingface.co/stabilityai/stablelm-2-zephyr-1_6b (opens in a new tab)

ollama run hf.co/stabilityai/stablelm-2-zephyr-1_6b

Original weights · Hugging Face

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

huggingface.co/stabilityai/stablelm-2-zephyr-1_6b (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 10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 46/100 (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 M5 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.	4.5 / 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.	2.4 / 15
Match score	46.9 / 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 Ultra (256 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	17.4 GB	192 GB	1,270 tok/s	Runs great	7Basic quality (D) · 7 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.
`Q3_K_M`	17.6 GB	192 GB	1,000 tok/s	Runs great	8Basic quality (D) · 8 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.
`Q4_K_M`	17.8 GB	192 GB	773 tok/s	Runs great	9Basic quality (D) · 9 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (Q4_0) (opens in a new tab)
`Q5_K_M`	17.9 GB	192 GB	639 tok/s	Runs great	9Basic quality (D) · 9 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	18.1 GB	192 GB	537 tok/s	Runs great	9Basic quality (D) · 9 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.
`Q8_0`	18.5 GB	192 GB	394 tok/s	Runs great	10Basic quality (D) · 10 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	20.0 GB	192 GB	181 tok/s	Runs great	10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.	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

10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 F16 · 47.8 tok/s · Runs great
10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 F16 · 61.2 tok/s · Runs great
10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GB F16 · 63.2 tok/s · Runs great
10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER F16 · 88.5 tok/s · Runs great
10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Pro (24 GB) F16 · 41.3 tok/s · Runs great
10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT F16 · 96.8 tok/s · Runs great

Quick answers

How much memory does StableLM 2 Zephyr 1.6B need on the M5 Ultra 256GB?

At F16 it needs about 20.0 GB. The M5 Ultra 256GB has 192 GB usable.

How fast is StableLM 2 Zephyr 1.6B on the M5 Ultra 256GB?

About 181 tok/s at F16, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of StableLM 2 Zephyr 1.6B should I use on the M5 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.