ToolSite

What LLMs can a Ryzen AI Max+ 395 (128 GB) run?

A Ryzen AI Max+ 395 (128 GB) gives a model 96 GB usable of memory (up to 96 GB can be assigned to the GPU) and 256 GB/s of bandwidth. Of the 40 open models tracked here, 24 fit at Q4_K_M with an 8,192-token context, and 1 more at a lower precision.

Models that fit on one Ryzen AI Max+ 395 (128 GB)

The most precise weights that still fit with 8K tokens of context and one request, the memory that takes, the longest context at that precision and the writing speed. Bigger models come first.

Model Best precision Memory Longest context Tokens/s
Qwen3.8 Flash Next 180.0B, 6B active GGUF Q3_K_M 90.8 GB 208K 24–40
Mistral Medium 3.5 128B 127.7B GGUF Q4_K_M 82.7 GB 43K 1.8–2.4
Qwen3.5 122B-A10B 125.1B, 10B active GGUF Q5_K_M 91.5 GB 181K 10–17
Nemotron 3 Super 120B-A12B 123.6B, 12B active GGUF Q5_K_M 90.3 GB 256K (full) 8.8–15
gpt-oss-120b 116.8B, 5.1B active GGUF Q5_K_M 85.6 GB 128K (full) 19–32
Qwen3-Coder-Next 79.7B, 3B active GGUF Q8_0 87.4 GB 256K (full) 22–37
Llama 3.1 70B 70.6B GGUF Q8_0 80.0 GB 54K 1.8–2.5
Qwen3.6 35B-A3B 36.0B, 3B active FP16 / BF16 74.3 GB 256K (full) 12–21
Nemotron 3 Nano 30B-A3B 31.6B, 3.5B active FP16 / BF16 65.3 GB 256K (full) 11–18
Gemma 4 31B 31.3B FP16 / BF16 65.8 GB 256K (full) 2.2–3.0
GLM-4.7 Flash 31.2B, 3B active FP16 / BF16 64.9 GB 198K (full) 12–20
Xing 4.0 29B-A4B 31.2B, 4B active FP16 / BF16 64.8 GB 256K (full) 9.0–15
Qwen3 30B-A3B 30.5B, 3.3B active FP16 / BF16 63.9 GB 40K (full) 10–17
Muse Glimmer 30B 29.8B FP16 / BF16 61.7 GB 128K (full) 2.3–3.2
Qwen3.6 27B 27.8B FP16 / BF16 58.0 GB 256K (full) 2.5–3.4
Qwen3.8 27B 27.8B FP16 / BF16 58.0 GB 256K (full) 2.5–3.4
Gemma 4 26B-A4B 25.8B, 4B active FP16 / BF16 53.7 GB 256K (full) 9.1–15
gpt-oss-20b 20.9B, 3.6B active FP16 / BF16 43.6 GB 128K (full) 10–17
Gemma 4 12B 12.0B FP16 / BF16 25.4 GB 256K (full) 5.7–7.9
Qwen3.5 9B 9.7B FP16 / BF16 20.6 GB 256K (full) 7.1–9.8
Qwen3 8B 8.2B FP16 / BF16 18.5 GB 40K (full) 7.9–11
Llama 3.1 8B 8.0B FP16 / BF16 18.1 GB 128K (full) 8.1–11
Gemma 4 E4B 8.0B FP16 / BF16 17.0 GB 128K (full) 8.6–12
Nemotron 3 Nano 4B 4.0B FP16 / BF16 8.78 GB 256K (full) 17–23
MiniCPM5 2B 2.5B FP16 / BF16 6.02 GB 128K (full) 25–35

Too big for one card

How many Ryzen AI Max+ 395 (128 GB) cards these need at Q4_K_M in one tensor-parallel group; some need more than 8.

How these numbers are worked out

Memory is the weights at each precision plus the KV cache for 8,192 tokens in FP16 and runtime overhead (0.5 GB plus 10%), computed from each model's files on Hugging Face with the LLM VRAM Calculator. Speed is estimated from memory bandwidth and the parameters read per token with the LLM Speed Calculator. Both tools take any other model from Hugging Face.

Other GPUs and Macs

Model numbers read from Hugging Face on .