Step 5 Preview (600B-A27B) on Apple M5 Ultra (512 GB)

Can the Apple M5 Ultra (512 GB) run Step 5 Preview (600B-A27B)?

Yes, it runs well (tight fit)

Runs well (tight fit). At Q3_K_M it needs about 328 GB of 384 GB usable, with an estimated speed of 50.7 tok/s.

Best quant: Q3_K_M
Generation speed: 50.7 tok/s
Prompt processing: 866 tok/s
First token (1K prompt): 1.2 s
Largest safe context: 781K

Best app to run it on the Apple M5 Ultra (512 GB)

On macOS

Docker Model Runner

Command line + local API · runs on llama.cpp, vLLM

Handy if you already work in Docker.

docker model run hf.co/stepfun-ai/Step-5-Preview-BF16

Text Generation WebUI

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 Step 5 Preview (600B-A27B)

Original weights · Hugging Face

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

huggingface.co/stepfun-ai/Step-5-Preview-BF16 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/stepfun-ai/Step-5-Preview (opens in a new tab)

git clone https://github.com/stepfun-ai/Step-5-Preview

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q3_K_M, 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 Ultra (512 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.	36.7 / 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.	15.0 / 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	90.7 / 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 (512 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	274 GB	384 GB	62.2 tok/s	Runs great	67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q3_K_M`	328 GB	384 GB	50.7 tok/s	Runs welltight fit	81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q4_K_M`	401 GB	384 GB	34.5 tok/s	Runs wellover GPU memory limit	92Excellent quality (A+) · 92 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q5_K_M`	461 GB	384 GB	29.0 tok/s	Slowfar over GPU memory limit	94Excellent quality (A+) · 94 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q6_K`	527 GB	384 GB	—	Won't run	96Excellent quality (A+) · 96 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q8_0`	672 GB	384 GB	—	Won't run	97Excellent quality (A+) · 97 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 13/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	1,241 GB	384 GB	—	Won't run	97Excellent quality (A+) · 97 of 100: how capable the model is at F16, whatever it runs on. Match score 13/100 (quality, fit, speed and memory use) sets the ranking.	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

81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (512 GB) Q3_K_M · 36.5 tok/s · Runs well (tight fit)
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI325X Q2_K · 175 tok/s · Runs well (tight fit)
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI350X Q2_K · 197 tok/s · Runs well (tight fit)
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip Q2_K · 127 tok/s · Runs well (offloads to RAM)
94Excellent quality (A+) · 94 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. AMD EPYC 7002 / 7003 series NAS (512 GB) Q5_K_M · 4.2 tok/s · Slow (tight fit)
81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Intel Xeon Silver (4100 to 4300 series) NAS (512 GB) Q3_K_M · 3.3 tok/s · Slow

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.