readygpu

Framework Desktop Ryzen AI Max+ 395 64GB vs AMD Radeon AI PRO R9700

For running models locally, priced in the US. At 8k context the first runs 62 models fully in memory, the second 54.

In short

The Framework Desktop Ryzen AI Max+ 395 64GB has more memory for models: 64 GB against 32 GB. At 8k context the Framework Desktop Ryzen AI Max+ 395 64GB runs 62 of the models we track fully in memory and the AMD Radeon AI PRO R9700 54; only the Framework Desktop Ryzen AI Max+ 395 64GB holds Qwen 3.5 122B-A10B. On the models both run fully in memory, the AMD Radeon AI PRO R9700 is about 2.5× as fast as the Framework Desktop Ryzen AI Max+ 395 64GB (estimated, median across models). In the US the Framework Desktop Ryzen AI Max+ 395 64GB costs $1,899 at eBay (used) and the AMD Radeon AI PRO R9700 $1,700 at Amazon: the AMD Radeon AI PRO R9700 is $199 cheaper.

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

Framework Desktop Ryzen AI Max+ 395 64GB

$1,899

eBay, used (asking)

Add to build
AMD Radeon AI PRO R9700

$1,700

Amazon

Add to build

Specifications

SpecFramework Desktop Ryzen AI Max+ 395 64GBAMD Radeon AI PRO R9700
ChipRyzen AI Max+ 395 (Radeon 8060S)–
Memory bus256-bit256-bit
Memory bandwidth256 GB/s640 GB/s
FP16 compute59.4 TFLOPS191 TFLOPS
SoftwareROCmROCm
Unified memory64 GB–
GPU can use by default48 GB–
GPU can use, tuned56 GB–
Operating systemlinux–
ProcessorRyzen AI Max+ 395–
Storage1000 GB–
GPU–Radeon AI PRO R9700
Memory–32 GB GDDR6
Board power–300 W
PCIe generation–Gen 5
PCIe lanes–x16

What each runs

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

ModelFramework Desktop Ryzen AI Max+ 395 64GBAMD Radeon AI PRO R9700
Qwen 3.8 27B5tok/sQ8_012tok/sQ8_0
Qwen 3.5 122B-A10B23tok/sUD-Q2_K_XLoffload
Qwen 3.6 27B5tok/sQ8_012tok/sQ8_0
Qwen3 Coder Next32tok/sQ4_K_Moffload
Gemma 4 31B4tok/sQ8_013tok/sQ6_K
Mistral Small 4 119B33tok/sUD-Q2_K_XLoffload
Qwen 3.6 35B-A3B26tok/sQ8_075tok/sQ6_K
Qwen 3.5 27B5tok/sQ8_012tok/sQ8_0
Gemma 4 26B-A4B19tok/sQ8_047tok/sQ8_0
GLM 4.5 Air10tok/sQ2_Koffload
Qwen3 Next 80B-A3B41tok/sQ4_K_Moffload
Qwen 3.5 35B-A3B26tok/sQ8_080tok/sQ6_K
GLM 4.7 Flash15tok/sQ8_037tok/sQ8_0
Devstral Small 2 24B5tok/sQ8_013tok/sQ8_0
Nemotron 3.5 Lightning 30B-A3B25tok/sUD-Q6_K_XLoffload
Kimi Linear 48B-A3B33tok/sQ6_K109tok/sQ4_K_M
gpt-oss 20B32tok/sMXFP480tok/sMXFP4
Qwen3 Coder 30B-A3B21tok/sQ8_065tok/sQ6_K
Qwen3 32B4tok/sQ8_012tok/sQ6_K
Gemma 4 12B11tok/sQ8_027tok/sQ8_0
Qwen 3.5 9B14tok/sQ8_036tok/sQ8_0
Mistral Small 3.2 24B5tok/sQ8_013tok/sQ8_0
Gemma 3 27B5tok/sQ8_012tok/sQ8_0
DeepSeek R1 Distill Qwen 32B4tok/sQ8_012tok/sQ6_K
Llama 3.3 70B3tok/sQ4_K_Moffload
Ministral 3 14B9tok/sQ8_022tok/sQ8_0
Qwen3 14B8tok/sQ8_021tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B14tok/sQ8_036tok/sQ8_0
Qwen3 8B14tok/sQ8_036tok/sQ8_0
Phi-4 14B8tok/sQ8_020tok/sQ8_0
Qwen 3.5 4B29tok/sQ8_073tok/sQ8_0
Ministral 3 8B14tok/sQ8_035tok/sQ8_0
Granite 4.2 8B13tok/sQ8_033tok/sQ8_0
Gemma 4 E4B17tok/sQ8_042tok/sQ8_0
LFM2.5 8B-A1B58tok/sQ8_0144tok/sQ8_0
Llama 3.1 8B18tok/sQ6_K46tok/sQ6_K
Qwen2.5 0.5B223tok/sQ8_0557tok/sQ8_0
Qwen3.5 0.8B151tok/sQ8_0378tok/sQ8_0
Qwen3.5 2B91tok/sQ5_K_M226tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B66tok/sQ8_0165tok/sQ8_0
MiniCPM5 2B46tok/sQ8_0116tok/sQ8_0
LFM2.5 2.6B42tok/sQ8_0104tok/sQ8_0
LFM2.5 VL 3B42tok/sQ8_0104tok/sQ8_0
granite vision 4.1 4b33tok/sQ8_082tok/sQ8_0
granite 4.2 3b31tok/sQ8_077tok/sQ8_0
LFM2.5 24B A2B30tok/sQ8_076tok/sQ8_0
Mellum2.1 12B A2.5B Thinking30tok/sQ8_075tok/sQ8_0
Kimi VL A3B Thinking 250625tok/sQ8_063tok/sQ8_0
Kimi VL A3B24tok/smlx-8bit60tok/smlx-8bit
DeepSeek R1 Distill Qwen 7B16tok/sQ8_041tok/sQ8_0
GLM 4 9B 041416tok/smlx-5bit41tok/smlx-5bit
DeepSeek R1 Distill Llama 8B15tok/sQ8_037tok/sQ8_0
Ministral 3 8B Reasoning 251214tok/sQ8_035tok/sQ8_0
GLM 4.6V Flash14tok/sQ8_034tok/sQ8_0
GLM 4.1V 9B Thinking12tok/smlx-8bit29tok/smlx-8bit
DeepSeek R1 Distill Qwen 14B8tok/sQ8_020tok/sQ8_0
Devstral Small 25075tok/sQ8_013tok/sQ8_0
Magistral Small 25065tok/sQ8_013tok/sQ8_0
Magistral Small 25075tok/sQ8_013tok/sQ8_0
Magistral Small 25095tok/sQ8_013tok/sQ8_0
granite 4.2 30b4tok/sQ8_013tok/sQ6_K
DeepSeek R1 Distill Llama 70B3tok/sQ4_K_Moffload
Nemotron 3 Super 120B-A12Bwon't runoffload
DeepSeek V4 Flashwon't runwon't run
GLM 5.3 Flashwon't runwon't run
Qwen 3.8 Flash Nextwon't runwon't run
MiniMax M2.7won't runwon't run
gpt-oss 120Bwon'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 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 4.5Vwon't runwon't run
GLM 4.6won't runwon't run
GLM 4.6Vwon'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 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 Framework Desktop Ryzen AI Max+ 395 64GB or the AMD Radeon AI PRO R9700?
Choose the Framework Desktop Ryzen AI Max+ 395 64GB to run bigger models. Choose the AMD Radeon AI PRO R9700 for speed. Choose the AMD Radeon AI PRO R9700 to spend less.
Which can run bigger models, the Framework Desktop Ryzen AI Max+ 395 64GB or the AMD Radeon AI PRO R9700?
At 8k context the Framework Desktop Ryzen AI Max+ 395 64GB runs 62 of the models we track fully in memory and the AMD Radeon AI PRO R9700 54; only the Framework Desktop Ryzen AI Max+ 395 64GB holds Qwen 3.5 122B-A10B.
Which is faster for local AI, the Framework Desktop Ryzen AI Max+ 395 64GB or the AMD Radeon AI PRO R9700?
On the models both run fully in memory, the AMD Radeon AI PRO R9700 is about 2.5× as fast as the Framework Desktop Ryzen AI Max+ 395 64GB (estimated, median across models).
What is the price difference between the Framework Desktop Ryzen AI Max+ 395 64GB and the AMD Radeon AI PRO R9700?
In the US the Framework Desktop Ryzen AI Max+ 395 64GB costs $1,899 at eBay (used) and the AMD Radeon AI PRO R9700 $1,700 at Amazon: the AMD Radeon AI PRO R9700 is $199 cheaper.

More comparisons