What AI models can the Ryzen AI Max+ 395 128GB run?

With 128 GB unified memory, the Ryzen AI Max+ 395 128GB runs 19 of 22 popular open models fully in fast memory at Q4_K_M or better (8K context). The largest that fit are Qwen3.5 122B-A10B (Q5_K_M), gpt-oss-120b (Q5_K_M), Llama 4 Scout (Q6_K). Fastest: Gemma 4 E2B at about 63 tokens/sec and Qwen3.6 35B-A3B at about 48 tokens/sec.

Check with your own RAM and context length

Model	Result	Best quant	Memory needed	Est. speed
Gemma 4 E2B small	Runs on GPU	Q8_0	6.1 GB	63 tok/s
Qwen3.6 35B-A3B MoE · coding	Runs on GPU	Q8_0	38.2 GB	48 tok/s
gpt-oss-120b MoE · reasoning	Runs on GPU	Q5_K_M	84.3 GB	42 tok/s
gpt-oss-20b MoE · reasoning	Runs on GPU	Q8_0	23.2 GB	40 tok/s
Ministral 3 3B small	Runs on GPU	Q8_0	4.8 GB	38 tok/s
Gemma 4 26B A4B MoE · vision	Runs on GPU	Q8_0	27.9 GB	38 tok/s
Gemma 4 E4B small · audio	Runs on GPU	Q8_0	9.3 GB	32 tok/s
Qwen3.5 122B-A10B MoE	Runs on GPU	Q5_K_M	88.1 GB	22 tok/s
Qwen3.5 9B general	Runs on GPU	Q8_0	11.3 GB	15 tok/s
Gemma 4 12B general · audio	Runs on GPU	Q8_0	13.8 GB	12 tok/s
Llama 4 Scout MoE · vision	Runs on GPU	Q6_K	91.4 GB	11 tok/s
Phi-4 14B reasoning	Runs on GPU	Q8_0	17.7 GB	9.8 tok/s
Mistral Small 3.1 24B general	Runs on GPU	Q8_0	27.3 GB	6.0 tok/s
Qwen3.6 27B coding	Runs on GPU	Q8_0	29.8 GB	5.4 tok/s
Qwen3.8 27B coding	Runs on GPU	Q8_0	30.6 GB	5.2 tok/s
Granite 4.2 30B general	Runs on GPU	Q8_0	31.9 GB	4.9 tok/s
Gemma 4 31B general · vision	Runs on GPU	Q8_0	33.8 GB	4.7 tok/s
Hermes 4.3 36B general	Runs on GPU	Q8_0	40.5 GB	4.0 tok/s
Llama 3.3 70B general	Runs on GPU	Q8_0	78.1 GB	2.0 tok/s
Qwen3.8-Flash-Next MoE	Lower quality fit	Q3_K_M	87.1 GB	52 tok/s
GLM-5.3-Flash MoE · coding	Too big	Q4_K_M	196.0 GB	—
DeepSeek V4.1-Flash MoE · coding	Too big	Q4_K_M	335.8 GB	—

Specs used: 128 GB unified memory, 256 GB/s memory bandwidth. Speeds are estimates for generating text with llama.cpp-style runtimes; real numbers usually land within about 20%.

Apps that support the Ryzen AI Max+ 395 128GB

Ollama LM Studio Jan GPT4All AnythingLLM llama.cpp vLLM SGLang KoboldCpp Text Generation WebUI LocalAI