Check my GPU

on

Can the Apple M2 Ultra (192 GB) run Step 3.5 Flash (196B-A11B)?

93 ptsExcellent (S) · 93 of 100 points: Model quality 39.3/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15

Yes, with little memory to spare

Tight fit. At Q4_K_M it needs about 134 GB of 144 GB usable, with an estimated speed of 38.4 tok/s.

Best quant
Q4_K_M
Generation speed
38.4 tok/s
Prompt processing
1,533 tok/s
First token (1K prompt)
0.7 s
Largest safe context
188K

Download Step 3.5 Flash (196B-A11B)

Recommended for the Apple M2 Ultra (192 GB): Q4_K_M. 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 Q4_K_M files (opens in a new tab)

huggingface.co/bartowski/stepfun-ai_Step-3.5-Flash-GGUF (opens in a new tab)

ollama run hf.co/bartowski/stepfun-ai_Step-3.5-Flash-GGUF

Original weights · Hugging Face

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

huggingface.co/stepfun-ai/Step-3.5-Flash (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-3.5-Flash (opens in a new tab)

git clone https://github.com/stepfun-ai/Step-3.5-Flash

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

How the S grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.39.3 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.24.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.14.7 / 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
Total93.0 / 10093 ptsExcellent (S) · 93 of 100 points: Model quality 39.3/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every quantization on the Apple M2 Ultra (192 GB)

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 92.3 GB 144 GB 63.1 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 29.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.8/15 GGUF · folder (opens in a new tab)
Q3_K_M 110 GB 144 GB 49.7 tok/s Runs well 89 ptsExcellent (S) · 89 of 100 points: Model quality 34.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 GGUF · folder (opens in a new tab)
Q4_K_M 134 GB 144 GB 38.4 tok/s Tight fit 93 ptsExcellent (S) · 93 of 100 points: Model quality 39.3/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15 GGUF · folder (opens in a new tab)
Q5_K_M 154 GB 144 GB 27.0 tok/s Runs with offload 77 ptsGreat (A) · 77 of 100 points: Model quality 40.2/45, Memory fit 10.0/25, Speed 12.3/15, Memory use 15.0/15 GGUF · folder (opens in a new tab)
Q6_K 176 GB 144 GB 22.7 tok/s Heavy offload 71 ptsGood (B) · 71 of 100 points: Model quality 41.0/45, Memory fit 4.0/25, Speed 11.3/15, Memory use 15.0/15 GGUF · folder (opens in a new tab)
Q8_0 224 GB 144 GB — Won't run 12 ptsWon't run (F) · 12 of 100 points: Model quality 12.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 GGUF · folder (opens in a new tab)
F16 411 GB 144 GB — Won't run 12 ptsWon't run (F) · 12 of 100 points: Model quality 12.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 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

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.