Check my GPU

on

Can the AMD Ryzen AI Max+ 395 (128 GB) run Step 3.5 Flash (196B-A11B)?

78 ptsGreat (A) · 78 of 100 points: Model quality 29.0/45, Memory fit 24.0/25, Speed 10.7/15, Memory use 15.0/15

Yes, with little memory to spare

Tight fit. At Q2_K it needs about 88.5 GB of 96.0 GB usable, with an estimated speed of 20.2 tok/s.

Best quant
Q2_K
Generation speed
20.2 tok/s
Prompt processing
3,348 tok/s
First token (1K prompt)
0.3 s
Largest safe context
146K

Download Step 3.5 Flash (196B-A11B)

Recommended for the AMD Ryzen AI Max+ 395 (128 GB): Q2_K. 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 Q2_K 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 6 days ago against Hugging Face, Ollama and GitHub.

How the A 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.29.0 / 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.10.7 / 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
Total78.6 / 10078 ptsGreat (A) · 78 of 100 points: Model quality 29.0/45, Memory fit 24.0/25, Speed 10.7/15, 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 AMD Ryzen AI Max+ 395 (128 GB)

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 88.5 GB 96.0 GB 20.2 tok/s Tight fit 78 ptsGreat (A) · 78 of 100 points: Model quality 29.0/45, Memory fit 24.0/25, Speed 10.7/15, Memory use 15.0/15 GGUF · folder (opens in a new tab)
Q3_K_M 106 GB 96.0 GB 13.5 tok/s Heavy offload 62 ptsGood (B) · 62 of 100 points: Model quality 34.8/45, Memory fit 4.0/25, Speed 8.7/15, Memory use 15.0/15 GGUF · folder (opens in a new tab)
Q4_K_M 130 GB 96.0 GB — Won't run 11 ptsWon't run (F) · 11 of 100 points: Model quality 11.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 GGUF · folder (opens in a new tab)
Q5_K_M 150 GB 96.0 GB — Won't run 12 ptsWon't run (F) · 12 of 100 points: Model quality 12.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 GGUF · folder (opens in a new tab)
Q6_K 172 GB 96.0 GB — Won't run 12 ptsWon't run (F) · 12 of 100 points: Model quality 12.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 GGUF · folder (opens in a new tab)
Q8_0 220 GB 96.0 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 407 GB 96.0 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.