What AI can a Ryzen AI Max+ 395 64 GB run?

Quick verdict

Ryzen AI Max+ 395 (Strix Halo), 64 GB can run 25 of the 31 models tracked here at a comfortable speed, and another 3 slowly. The largest chat or coding model that fits is Qwen 3.6 35B A3B, which needs about 24.6 GB and generates roughly 33 words a second. The quickest is Gemma 4 E2B at about 58 words a second, which feels faster than you can read.

What limits this machine

Machines like this share fast soldered memory between the processor and the GPU, and the BIOS decides how much the GPU may use. About 58 GB of the 64 GB is usable here, at 256 GB/s. That makes large models affordable compared with a high-end graphics card, though the memory is slower than Apple's Max-class chips.

What it is good for

Chat and coding

Best chat pick: Qwen 3.5 35B A3B at about 35 words a second. Best coding pick: Qwen 3.6 35B A3B at about 33.

Images

• Stable Diffusion XL: runs great, about about 11 s per image
• FLUX.2 klein 4B: runs great, about about 19 s per image
• Z-Image Turbo 6B: runs great, about about 27 s per image

Video

• LTX-2.3: runs great, about about 2 min per 4 second clip
• Wan 2.2 5B: runs great, about about 7 min per 4 second clip
• Wan 2.2 14B: runs great, about about 14 min per 4 second clip

Voice and music

• Whisper large-v3 turbo: runs great, about about 42 s per 10 minutes of audio
• Kokoro TTS: runs great, about about 6 s per minute of speech
• Qwen3 TTS 1.7B: runs great, about about 30 s per minute of speech
• ACE-Step 1.5: runs great, about about 1 min per 1 minute song

Fastest models here

• Gemma 4 E2B: about 58 words a second, faster than you can read
• Gemma 4 E4B: about 36 words a second, smooth
• Qwen 3.5 4B: about 35 words a second, smooth
• Qwen 3.5 35B A3B: about 35 words a second, smooth
• Qwen 3.6 35B A3B: about 33 words a second, smooth

Memory headroom

Spare memory after loading the model decides how long a conversation or document can be before things slow down. With about 58 GB usable here:

• Qwen 3.6 35B A3B needs 24.6 GB, leaving 33 GB spare, plenty for long documents.
• Qwen 3.5 35B A3B needs 23.6 GB, leaving 34 GB spare, plenty for long documents.
• Qwen3 Coder 30B needs 20.4 GB, leaving 37.2 GB spare, plenty for long documents.
• Qwen 3.6 27B needs 19.9 GB, leaving 37.7 GB spare, plenty for long documents.
• Gemma 4 26B A4B needs 19.4 GB, leaving 38.2 GB spare, plenty for long documents.

What does not fit, and by how much

• gpt-oss 120B needs about 68.8 GB and this machine tops out near 58 GB, so it is about 11 GB short.
• Qwen 3.5 122B A10B needs about 85.5 GB and this machine tops out near 58 GB, so it is about 28 GB short.
• DeepSeek V3 671B needs about 424.7 GB and this machine tops out near 58 GB, so it is about 367 GB short.

How it compares

• Ryzen AI Max+ 395 (Strix Halo), 128 GB: 2 more models; adds Qwen 3.5 122B A10B, gpt-oss 120B.
• NVIDIA DGX Spark, 128 GB: 4 more models; adds Gemma 4 31B, Qwen 3.5 122B A10B, gpt-oss 120B and more.

Is an upgrade worth it?

The biggest single jump is Mac with M3 Ultra, 256 GB, which would unlock 5 more models, including Gemma 4 31B, Llama 3.3 70B, Qwen 3.5 122B A10B.

Questions