readygpu

Beelink GTR9 Pro Ryzen AI Max+ 395 128GB vs NVIDIA RTX A6000

For running models locally, priced in Canada. At 128k context the first runs 73 models fully in memory, the second 60.

In short

The Beelink GTR9 Pro Ryzen AI Max+ 395 128GB has more memory for models: 128 GB against 48 GB. At 128k context the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB runs 73 of the models we track fully in memory and the NVIDIA RTX A6000 60; only the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB holds Qwen 3.8 Flash Next. On the models both run fully in memory, the NVIDIA RTX A6000 is about 3.4× as fast as the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB (estimated, median across models). In Canada the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB costs $5,519 at Amazon and the NVIDIA RTX A6000 $7,000 at Amazon: the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB is $1,481 cheaper.

Updated . Speeds are estimates; how they are worked out.

Beelink GTR9 Pro Ryzen AI Max+ 395 128GB

$5,519

Amazon

Add to build
NVIDIA RTX A6000

$7,000

Amazon

Add to build

Specifications

SpecBeelink GTR9 Pro Ryzen AI Max+ 395 128GBNVIDIA RTX A6000
ChipRyzen AI Max+ 395 (Radeon 8060S)–
Memory bus256-bit384-bit
Memory bandwidth256 GB/s768 GB/s
FP16 compute59.4 TFLOPS38.71 TFLOPS
SoftwareROCmCUDA
Unified memory128 GB–
GPU can use by default96 GB–
GPU can use, tuned120 GB–
Operating systemwindows–
ProcessorRyzen AI Max+ 395–
Storage2000 GB–
GPU–RTX A6000
Memory–48 GB GDDR6
Board power–300 W
PCIe generation–Gen 4
PCIe lanes–x16

What each runs

Estimated decode speed with the most precise quant that fits each one est.

ModelBeelink GTR9 Pro Ryzen AI Max+ 395 128GBNVIDIA RTX A6000
Qwen 3.8 Flash Next3tok/sUD-Q3_K_XLwon't run
Qwen 3.8 27B4tok/sQ8_013tok/sQ8_0
Qwen 3.5 122B-A10B8tok/sQ5_K_M43tok/sUD-Q2_K_XL
Qwen 3.6 27B4tok/sQ8_013tok/sQ8_0
Qwen3 Coder Next11tok/sQ8_0offload
gpt-oss 120B11tok/sMXFP4offload
Nemotron 3 Super 120B-A12B8tok/sQ5_K_Moffload
Gemma 4 31B3tok/sQ8_011tok/sQ8_0
Mistral Small 4 119B10tok/sQ6_K53tok/sUD-Q2_K_XL
Qwen 3.6 35B-A3B15tok/sQ8_049tok/sQ8_0
Qwen 3.5 27B4tok/sQ8_013tok/sQ8_0
Gemma 4 26B-A4B12tok/sQ8_041tok/sQ8_0
GLM 4.5 Air3tok/sQ4_K_Moffload
Qwen 3.5 35B-A3B15tok/sQ8_049tok/sQ8_0
Qwen3 Next 80B-A3B13tok/sQ8_0offload
GLM 4.7 Flash7tok/sQ8_023tok/sQ8_0
Devstral Small 2 24B3tok/sQ8_010tok/sQ8_0
Nemotron 3.5 Lightning 30B-A3B20tok/sUD-Q6_K_XL68tok/sUD-Q6_K_XL
Kimi Linear 48B-A3B20tok/sQ8_080tok/sQ6_K
gpt-oss 20B15tok/sMXFP451tok/sMXFP4
Qwen3 Coder 30B-A3B5tok/sQ8_018tok/sQ8_0
Qwen3 32B2tok/sQ8_0offload
Gemma 4 12B9tok/sQ8_031tok/sQ8_0
Qwen 3.5 9B10tok/sQ8_034tok/sQ8_0
Gemma 3 27B4tok/sQ8_012tok/sQ8_0
Mistral Small 3.2 24B3tok/sQ8_010tok/sQ8_0
DeepSeek R1 Distill Qwen 32B2tok/sQ8_0offload
Llama 3.3 70B2tok/sQ5_K_Mwon't run
Ministral 3 14B4tok/sQ8_013tok/sQ8_0
Qwen3 14B4tok/sQ8_013tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B5tok/sQ8_017tok/sQ8_0
Qwen3 8B5tok/sQ8_017tok/sQ8_0
Phi-4 14B3tok/sQ8_011tok/sQ8_0
Qwen 3.5 4B16tok/sQ8_054tok/sQ8_0
Ministral 3 8B5tok/sQ8_018tok/sQ8_0
Granite 4.2 8B5tok/sQ8_015tok/sQ8_0
Gemma 4 E4B12tok/sQ8_040tok/sQ8_0
LFM2.5 8B-A1B11tok/sQ8_038tok/sQ8_0
Llama 3.1 8B6tok/sQ6_K20tok/sQ6_K
Qwen2.5 0.5B66tok/sQ8_0222tok/sQ8_0
Qwen3.5 0.8B58tok/sQ8_0195tok/sQ8_0
Qwen3.5 2B46tok/sQ5_K_M155tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B25tok/sQ8_084tok/sQ8_0
Mellum2.1 12B A2.5B Thinking18tok/sQ8_062tok/sQ8_0
Spark X2.5 4B18tok/smlx-4bit60tok/smlx-4bit
MiniCPM5 2B17tok/sQ8_057tok/sQ8_0
FrogNano 4B 260916tok/sQ8_053tok/sQ8_0
LFM2.5 2.6B13tok/sQ8_044tok/sQ8_0
LFM2.5 VL 3B13tok/sQ8_044tok/sQ8_0
Kimi VL A3B Thinking 250612tok/sQ8_040tok/sQ8_0
Kimi VL A3B12tok/smlx-8bit39tok/smlx-8bit
GLM 4 9B 041410tok/smlx-5bit35tok/smlx-5bit
granite vision 4.1 4b10tok/sQ8_033tok/sQ8_0
granite 4.2 3b10tok/sQ8_033tok/sQ8_0
GLM 4.6V Flash9tok/sQ8_031tok/sQ8_0
DeepSeek R1 Distill Qwen 7B9tok/sQ8_031tok/sQ8_0
GLM 4.1V 9B Thinking8tok/smlx-8bit28tok/smlx-8bit
Ministral 3 3B Instruct 25128tok/sQ8_027tok/sQ8_0
LFM2.5 24B A2B7tok/sQ8_022tok/sQ8_0
DeepSeek R1 Distill Llama 8B6tok/sQ8_019tok/sQ8_0
Ministral 3 8B Reasoning 25125tok/sQ8_018tok/sQ8_0
Qwen3.8 27B OBLITERATED5tok/smlx-4bit16tok/smlx-4bit
Muse Glimmer 30B4tok/sQ8_014tok/sQ8_0
Ministral 3 14B Reasoning 25124tok/sQ8_013tok/sQ8_0
DeepSeek R1 Distill Qwen 14B3tok/sQ8_012tok/sQ8_0
Devstral Small 25073tok/sQ8_010tok/sQ8_0
Magistral Small 25063tok/sQ8_010tok/sQ8_0
Magistral Small 25073tok/sQ8_010tok/sQ8_0
Magistral Small 25093tok/sQ8_010tok/sQ8_0
GLM 4.5V3tok/sQ4_K_Mwon't run
GLM 4.6V3tok/sQ4_K_Mwon't run
granite 4.2 30b2tok/sQ8_0offload
DeepSeek R1 Distill Llama 70B2tok/sQ5_K_Mwon't run
DeepSeek V4 Flashwon't runwon't run
GLM 5.3 Flashwon't runwon't run
MiniMax M2.7won't runwon't run
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek R1 Zerowon't runwon't run
DeepSeek V3won't runwon't run
DeepSeek V3 0324won't runwon't run
DeepSeek V3.1won't runwon't run
DeepSeek V3.1 Terminuswon't runwon't run
DeepSeek V3.2won't runwon't run
DeepSeek V4 Flash 0731won't runwon't run
DeepSeek V4 Flash Vision Expwon't runwon't run
Devstral 2 123B Instruct 2512won't runwon't run
GLM 4.5won't runwon't run
GLM 4.6won't runwon't run
GLM 4.7won't runwon't run
GLM 5won't runwon't run
GLM 5.1won't runwon't run
GLM 5.2won't runwon't run
GLM 5.3won't runwon't run
Kimi Dev 72Bwon't runwon't run
Kimi K2won't runwon't run
Kimi K2 Instruct 0905won't runwon't run
Kimi K2 Thinkingwon't runwon't run
Kimi K2.5won't runwon't run
MiniMax M2won't runwon't run
MiniMax M2.1won't runwon't run
MiniMax M2.5won't runwon't run
MiniMax M3won't runwon't run
Mistral Medium 3.5 128Bwon't runwon't run

Questions

Which is better for local AI, the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB or the NVIDIA RTX A6000?
Choose the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB to run bigger models. Choose the NVIDIA RTX A6000 for speed. Choose the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB to spend less.
Which can run bigger models, the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB or the NVIDIA RTX A6000?
At 128k context the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB runs 73 of the models we track fully in memory and the NVIDIA RTX A6000 60; only the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB holds Qwen 3.8 Flash Next.
Which is faster for local AI, the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB or the NVIDIA RTX A6000?
On the models both run fully in memory, the NVIDIA RTX A6000 is about 3.4× as fast as the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB (estimated, median across models).
What is the price difference between the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB and the NVIDIA RTX A6000?
In Canada the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB costs $5,519 at Amazon and the NVIDIA RTX A6000 $7,000 at Amazon: the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB is $1,481 cheaper.

More comparisons

More hardware for local AI