readygpu

Beelink GTR9 Pro Ryzen AI Max+ 395 128GB vs NVIDIA DGX Spark 128GB

For running models locally, priced in the US. At 64k context the first runs 71 models fully in memory, the second 73.

In short

Both have 128 GB of memory for models; the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB has 256 GB/s of bandwidth and the NVIDIA DGX Spark 128GB 273 GB/s. At 64k context the NVIDIA DGX Spark 128GB runs 73 of the models we track fully in memory and the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB 71; only the NVIDIA DGX Spark 128GB holds DeepSeek V4 Flash. On the models both run fully in memory, the NVIDIA DGX Spark 128GB is about 1.2× as fast as the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB (estimated, median across models).

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

Beelink GTR9 Pro Ryzen AI Max+ 395 128GB

Not priced here

Add to build
NVIDIA DGX Spark 128GB

$7,699

eBay

Add to build

Specifications

SpecBeelink GTR9 Pro Ryzen AI Max+ 395 128GBNVIDIA DGX Spark 128GB
ChipRyzen AI Max+ 395 (Radeon 8060S)GB10 Grace Blackwell
Memory bus256-bit256-bit
Memory bandwidth256 GB/s273 GB/s
FP16 compute59.4 TFLOPS62 TFLOPS
SoftwareROCmCUDA
Unified memory128 GB128 GB
GPU can use by default96 GB119 GB
GPU can use, tuned120 GB122 GB
Operating systemwindowsdgx-os
ProcessorRyzen AI Max+ 39520-core Arm (GB10)
Storage2000 GB4000 GB

What each runs

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

ModelBeelink GTR9 Pro Ryzen AI Max+ 395 128GBNVIDIA DGX Spark 128GB
DeepSeek V4 Flashwon't run8tok/sUD-Q2_K_XL
Qwen 3.8 Flash Next3tok/sUD-Q3_K_XL2tok/sQ4_K_M
GLM 5.3 Flashwon't run11tok/sUD-Q2_K_XL
MiniMax M2.74tok/sUD-Q2_K_XL5tok/sUD-Q3_K_M
Qwen 3.8 27B4tok/sQ8_05tok/sQ8_0
Qwen 3.5 122B-A10B9tok/sQ5_K_M10tok/sQ6_K
Qwen 3.6 27B4tok/sQ8_05tok/sQ8_0
gpt-oss 120B15tok/sMXFP418tok/sMXFP4
Qwen3 Coder Next15tok/sQ8_018tok/sQ8_0
Nemotron 3 Super 120B-A12B8tok/sQ5_K_M9tok/sUD-Q6_K
Gemma 4 31B4tok/sQ8_04tok/sQ8_0
Mistral Small 4 119B11tok/sUD-Q6_K14tok/sUD-Q6_K
Qwen 3.6 35B-A3B19tok/sQ8_023tok/sQ8_0
Qwen 3.5 27B4tok/sQ8_05tok/sQ8_0
Gemma 4 26B-A4B15tok/sQ8_018tok/sQ8_0
GLM 4.5 Air3tok/sQ5_K_M4tok/sQ6_K
Qwen 3.5 35B-A3B19tok/sQ8_023tok/sQ8_0
Qwen3 Next 80B-A3B18tok/sQ8_021tok/sQ8_0
GLM 4.7 Flash10tok/sQ8_012tok/sQ8_0
Devstral Small 2 24B4tok/sQ8_05tok/sQ8_0
Nemotron 3.5 Lightning 30B-A3B22tok/sUD-Q6_K_XL27tok/sUD-Q6_K_XL
Kimi Linear 48B-A3B23tok/sQ8_027tok/sQ8_0
gpt-oss 20B21tok/sMXFP425tok/sMXFP4
Qwen3 Coder 30B-A3B9tok/sQ8_011tok/sQ8_0
Qwen3 32B3tok/sQ8_03tok/sQ8_0
Gemma 4 12B10tok/sQ8_012tok/sQ8_0
Qwen 3.5 9B12tok/sQ8_014tok/sQ8_0
Gemma 3 27B4tok/sQ8_05tok/sQ8_0
Mistral Small 3.2 24B4tok/sQ8_05tok/sQ8_0
DeepSeek R1 Distill Qwen 32B3tok/sQ8_03tok/sQ8_0
Llama 3.3 70B2tok/sQ8_02tok/sQ8_0
Ministral 3 14B6tok/sQ8_07tok/sQ8_0
Qwen3 14B5tok/sQ8_06tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B8tok/sQ8_09tok/sQ8_0
Qwen3 8B8tok/sQ8_09tok/sQ8_0
Phi-4 14B5tok/sQ8_06tok/sQ8_0
Qwen 3.5 4B21tok/sQ8_025tok/sQ8_0
Ministral 3 8B8tok/sQ8_09tok/sQ8_0
Granite 4.2 8B7tok/sQ8_08tok/sQ8_0
Gemma 4 E4B14tok/sQ8_017tok/sQ8_0
LFM2.5 8B-A1B20tok/sQ8_024tok/sQ8_0
Llama 3.1 8B9tok/sQ6_K11tok/sQ6_K
Qwen2.5 0.5B105tok/sQ8_0127tok/sQ8_0
Qwen3.5 0.8B86tok/sQ8_0104tok/sQ8_0
Qwen3.5 2B62tok/sQ5_K_M75tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B37tok/sQ8_045tok/sQ8_0
MiniCPM5 2B26tok/sQ8_031tok/sQ8_0
Mellum2.1 12B A2.5B Thinking23tok/sQ8_028tok/sQ8_0
LFM2.5 2.6B20tok/sQ8_025tok/sQ8_0
LFM2.5 VL 3B20tok/sQ8_025tok/sQ8_0
Kimi VL A3B Thinking 250616tok/sQ8_020tok/sQ8_0
Kimi VL A3B16tok/smlx-8bit19tok/smlx-8bit
granite vision 4.1 4b16tok/sQ8_019tok/sQ8_0
granite 4.2 3b15tok/sQ8_018tok/sQ8_0
GLM 4 9B 041413tok/smlx-5bit16tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B12tok/sQ8_014tok/sQ8_0
LFM2.5 24B A2B11tok/sQ8_014tok/sQ8_0
GLM 4.6V Flash11tok/sQ8_013tok/sQ8_0
GLM 4.1V 9B Thinking10tok/smlx-8bit12tok/smlx-8bit
DeepSeek R1 Distill Llama 8B8tok/sQ8_010tok/sQ8_0
Ministral 3 8B Reasoning 25128tok/sQ8_09tok/sQ8_0
DeepSeek R1 Distill Qwen 14B5tok/sQ8_06tok/sQ8_0
GLM 4.5V4tok/sQ4_K_M4tok/sQ8_0
Devstral Small 25074tok/sQ8_05tok/sQ8_0
GLM 4.6V4tok/sQ4_K_M4tok/sQ8_0
Magistral Small 25064tok/sQ8_05tok/sQ8_0
Magistral Small 25074tok/sQ8_05tok/sQ8_0
Magistral Small 25094tok/sQ8_05tok/sQ8_0
granite 4.2 30b3tok/sQ8_04tok/sQ8_0
DeepSeek R1 Distill Llama 70B2tok/sQ8_02tok/sQ8_0
Devstral 2 123B Instruct 25121tok/sQ4_K_M1tok/sQ6_K
Kimi Dev 72B1tok/sQ8_02tok/sQ8_0
Mistral Medium 3.5 128B1tok/sQ4_K_M1tok/sQ6_K
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek R1 Zerowon'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
GLM 4.6won't runwon't run
GLM 4.7won'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 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

Questions

Which is better for local AI, the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB or the NVIDIA DGX Spark 128GB?
Choose the NVIDIA DGX Spark 128GB to run bigger models. Choose the NVIDIA DGX Spark 128GB for speed.
Which can run bigger models, the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB or the NVIDIA DGX Spark 128GB?
At 64k context the NVIDIA DGX Spark 128GB runs 73 of the models we track fully in memory and the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB 71; only the NVIDIA DGX Spark 128GB holds DeepSeek V4 Flash.
Which is faster for local AI, the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB or the NVIDIA DGX Spark 128GB?
On the models both run fully in memory, the NVIDIA DGX Spark 128GB is about 1.2× as fast as the Beelink GTR9 Pro Ryzen AI Max+ 395 128GB (estimated, median across models).

More comparisons