Is the Ryzen AI Max+ PRO 495 faster than the M5 Max for LLMs?

The M5 Max reads memory about 125% faster than the Ryzen AI Max+ PRO 495 (614 vs 273 GB/s), so it writes about 125% faster with any model that fits both. llama.cpp’s public benchmarks have no result for the Ryzen AI Max+ PRO 495 yet, so prompt reading isn’t compared here.

Which can run bigger models, the M5 Max or the Ryzen AI Max+ PRO 495?

The Ryzen AI Max+ PRO 495 has about 144 GB for models, the M5 Max about 96 GB. 47 of 73 popular open models run well on the M5 Max, 41 on the Ryzen AI Max+ PRO 495.

Can MLX Node run on the Ryzen AI Max+ PRO 495?

No. MLX Node and MLX Harness run on Apple Silicon Macs only, with Apple’s MLX framework.

M5 Max vs Ryzen AI Max+ PRO 495 for local LLMs: memory, speed, which to buy

Side by side

	M5 Max	Ryzen AI Max+ PRO 495
What it is	MacBook Pro (14-inch, M5 Pro or M5 Max), MacBook Pro (16-inch, M5 Pro or M5 Max), Mac Studio (M5 Max or M5 Ultra)	A complete small computer
Memory sizes	36, 48, 64, 128 GB	192 GB
Memory bandwidth	460–614 GB/s	273 GB/s
For models, at most	about 96 GB	about 144 GB
Models that run well	47 of 73	41 of 73
Measured: writing	120 tok/s	not measured
Measured: reading a prompt	3,220 tok/s	not measured

For models we count about 75% of memory on both, the macOS default, because the Ryzen AI Max+ PRO 495 also shares one memory pool between its CPU and GPU. How much its GPU may really use depends on its operating system and settings.

Where each one wins

Writing speed. The M5 Max reads memory about 125% faster than the Ryzen AI Max+ PRO 495 (614 vs 273 GB/s), so it writes about 125% faster with any model that fits both.
Model size. The Ryzen AI Max+ PRO 495 has about 144 GB for models, the M5 Max about 96 GB. 47 of 73 popular open models run well on the M5 Max, 41 on the Ryzen AI Max+ PRO 495.
Reading long prompts. llama.cpp’s public benchmarks have no result for the Ryzen AI Max+ PRO 495 yet, so prompt reading isn’t compared here.
Software. The Ryzen AI Max+ PRO 495 runs Windows or Linux, and llama.cpp runs on its GPU with Vulkan. Software that needs NVIDIA’s CUDA runs on neither machine.
Around it. Both are complete computers that keep the model in one memory pool shared by the CPU and GPU.
The Mac. It’s also an everyday computer, and it runs MLX Harness and MLX Node, which are made for Apple Silicon.

Speed with popular models

Tokens a second for one conversation, each chip at its largest memory size (128 GB and 192 GB), with the best version of the model that fits.

Model	M5 Max	Ryzen AI Max+ PRO 495
Llama 3.1 8B Instruct8B	33–58 8-bit	14–26 8-bit
gpt-oss-20b21B · 3.6B active	145–259 native 4.25-bit	65–115 native 4.25-bit
Qwen3.6 35B A3B35B · 3B active	86–154 8-bit	38–68 8-bit
Qwen3.8 27B27B	10–17 8-bit	4–8 8-bit
Llama 3.3 70B Instruct70B	4–7 8-bit	2–3 8-bit
gpt-oss-120b117B · 5.1B active	102–182 native 4.25-bit	45–81 native 4.25-bit
Qwen3.5 122B A10B122B · 10B active	49–88 4-bit	12–21 8-bit
DeepSeek V4 Flash 0731284B · 13B active	67–120 2-bit lower quality	22–38 3-bit lower quality

Questions

Is the Ryzen AI Max+ PRO 495 faster than the M5 Max for LLMs?: The M5 Max reads memory about 125% faster than the Ryzen AI Max+ PRO 495 (614 vs 273 GB/s), so it writes about 125% faster with any model that fits both. llama.cpp’s public benchmarks have no result for the Ryzen AI Max+ PRO 495 yet, so prompt reading isn’t compared here.
Which can run bigger models, the M5 Max or the Ryzen AI Max+ PRO 495?: The Ryzen AI Max+ PRO 495 has about 144 GB for models, the M5 Max about 96 GB. 47 of 73 popular open models run well on the M5 Max, 41 on the Ryzen AI Max+ PRO 495.
Can MLX Node run on the Ryzen AI Max+ PRO 495?: No. MLX Node and MLX Harness run on Apple Silicon Macs only, with Apple’s MLX framework.

More comparisons

The M5 Max for local AI · Compare every model · The best Mac for local LLMs

How it’s worked out

Memory: the model’s parameters at 8, 6, 4, 3 or 2 bits per weight plus MLX’s group scales (half a bit per weight), or its native format, with room for the context on top. By default macOS lets the GPU use about 75% of unified memory. Speed: memory bandwidth divided by the bytes read per token is the ceiling for one conversation; in llama.cpp’s public Apple Silicon benchmarks real runs reach about 45% to 80% of it, which is the range shown. These are estimates, not measurements: measure your own Mac on MLX Bench. Model figures from each official model card, chip figures from Apple’s Tech Specs. Checked 2026-10-19. Same data as mlx.app/compare.

The Ryzen AI Max+ PRO 495’s bandwidth is worked out from AMD’s bus width and memory speed, as AMD doesn’t state it in GB/s. Ryzen AI Max+ PRO 495 figures: AMD: Ryzen AI Max+ PRO 495, Framework: Desktop specs.