readygpu

Framework Desktop Ryzen AI Max+ 395 64GB vs Mac mini M4 32GB

For running models locally, priced in the US. At 8k context the first runs 62 models fully in memory, the second 52.

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 Mac mini M4 32GB 52; only the Framework Desktop Ryzen AI Max+ 395 64GB holds Qwen 3.5 122B-A10B. On the models both run fully in memory, the Framework Desktop Ryzen AI Max+ 395 64GB is about 1.8× as fast as the Mac mini M4 32GB (estimated, median across models). In the US the Framework Desktop Ryzen AI Max+ 395 64GB costs $1,899 at eBay (used) and the Mac mini M4 32GB $1,420 at eBay: the Mac mini M4 32GB is $479 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
Mac mini M4 32GB

$1,420

eBay

Add to build

Specifications

SpecFramework Desktop Ryzen AI Max+ 395 64GBMac mini M4 32GB
ChipRyzen AI Max+ 395 (Radeon 8060S)Apple M4 (10-core GPU)
Memory bus256-bit128-bit
Memory bandwidth256 GB/s120 GB/s
FP16 compute59.4 TFLOPS3.76 TFLOPS
SoftwareROCmMetal
Unified memory64 GB32 GB
GPU can use by default48 GB21.3 GB
GPU can use, tuned56 GB24 GB
Operating systemlinuxmacos
ProcessorRyzen AI Max+ 395M4 10-core
Storage1000 GB512 GB

What each runs

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

ModelFramework Desktop Ryzen AI Max+ 395 64GBMac mini M4 32GB
Qwen 3.8 27B5tok/sQ8_04tok/sQ5_K_M
Qwen 3.5 122B-A10B23tok/sUD-Q2_K_XLwon't run
Qwen 3.6 27B5tok/sQ8_04tok/sQ5_K_M
Qwen3 Coder Next32tok/sQ4_K_Mwon't run
Gemma 4 31B4tok/sQ8_04tok/sQ4_K_M
Mistral Small 4 119B33tok/sUD-Q2_K_XLwon't run
Qwen 3.6 35B-A3B26tok/sQ8_023tok/sMXFP4
Qwen 3.5 27B5tok/sQ8_04tok/sQ5_K_M
Gemma 4 26B-A4B19tok/sQ8_013tok/sUD-Q5_K_M
GLM 4.5 Air10tok/sQ2_Kwon't run
Qwen3 Next 80B-A3B41tok/sQ4_K_Mwon't run
Qwen 3.5 35B-A3B26tok/sQ8_0won't run
GLM 4.7 Flash15tok/sQ8_012tok/sQ5_K_M
Devstral Small 2 24B5tok/sQ8_04tok/sQ6_K
Nemotron 3.5 Lightning 30B-A3B25tok/sUD-Q6_K_XLwon't run
Kimi Linear 48B-A3B33tok/sQ6_Kwon't run
gpt-oss 20B32tok/sMXFP418tok/sMXFP4
Qwen3 Coder 30B-A3B21tok/sQ8_018tok/sQ4_K_M
Qwen3 32B4tok/sQ8_04tok/sQ4_K_M
Gemma 4 12B11tok/sQ8_06tok/sQ8_0
Qwen 3.5 9B14tok/sQ8_08tok/sQ8_0
Mistral Small 3.2 24B5tok/sQ8_04tok/sQ6_K
Gemma 3 27B5tok/sQ8_04tok/sQ5_K_M
DeepSeek R1 Distill Qwen 32B4tok/sQ8_04tok/sQ4_K_M
Llama 3.3 70B3tok/sQ4_K_Mwon't run
Ministral 3 14B9tok/sQ8_05tok/sQ8_0
Qwen3 14B8tok/sQ8_05tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B14tok/sQ8_08tok/sQ8_0
Qwen3 8B14tok/sQ8_08tok/sQ8_0
Phi-4 14B8tok/sQ8_05tok/sQ8_0
Qwen 3.5 4B29tok/sQ8_016tok/sQ8_0
Ministral 3 8B14tok/sQ8_08tok/sQ8_0
Granite 4.2 8B13tok/sQ8_07tok/sQ8_0
Gemma 4 E4B17tok/sQ8_09tok/sQ8_0
LFM2.5 8B-A1B58tok/sQ8_032tok/sQ8_0
Llama 3.1 8B18tok/sQ6_K10tok/sQ6_K
Qwen2.5 0.5B223tok/sQ8_0124tok/sQ8_0
Qwen3.5 0.8B151tok/sQ8_084tok/sQ8_0
Qwen3.5 2B91tok/sQ5_K_M50tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B66tok/sQ8_037tok/sQ8_0
MiniCPM5 2B46tok/sQ8_026tok/sQ8_0
LFM2.5 2.6B42tok/sQ8_023tok/sQ8_0
LFM2.5 VL 3B42tok/sQ8_023tok/sQ8_0
granite vision 4.1 4b33tok/sQ8_018tok/sQ8_0
granite 4.2 3b31tok/sQ8_017tok/sQ8_0
LFM2.5 24B A2B30tok/sQ8_019tok/sQ6_K
Mellum2.1 12B A2.5B Thinking30tok/sQ8_017tok/sQ8_0
Kimi VL A3B Thinking 250625tok/sQ8_014tok/sQ8_0
Kimi VL A3B24tok/smlx-8bit13tok/smlx-8bit
DeepSeek R1 Distill Qwen 7B16tok/sQ8_09tok/sQ8_0
GLM 4 9B 041416tok/smlx-5bit9tok/smlx-5bit
DeepSeek R1 Distill Llama 8B15tok/sQ8_08tok/sQ8_0
Ministral 3 8B Reasoning 251214tok/sQ8_08tok/sQ8_0
GLM 4.6V Flash14tok/sQ8_08tok/sQ8_0
GLM 4.1V 9B Thinking12tok/smlx-8bit6tok/smlx-8bit
DeepSeek R1 Distill Qwen 14B8tok/sQ8_05tok/sQ8_0
Devstral Small 25075tok/sQ8_04tok/sQ5_K_M
Magistral Small 25065tok/sQ8_04tok/sQ6_K
Magistral Small 25075tok/sQ8_04tok/sQ5_K_M
Magistral Small 25095tok/sQ8_04tok/sQ5_K_M
granite 4.2 30b4tok/sQ8_04tok/sQ4_K_M
DeepSeek R1 Distill Llama 70B3tok/sQ4_K_Mwon't run
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
Nemotron 3 Super 120B-A12Bwon'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 Mac mini M4 32GB?
Choose the Framework Desktop Ryzen AI Max+ 395 64GB to run bigger models. Choose the Framework Desktop Ryzen AI Max+ 395 64GB for speed. Choose the Mac mini M4 32GB to spend less.
Which can run bigger models, the Framework Desktop Ryzen AI Max+ 395 64GB or the Mac mini M4 32GB?
At 8k context the Framework Desktop Ryzen AI Max+ 395 64GB runs 62 of the models we track fully in memory and the Mac mini M4 32GB 52; 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 Mac mini M4 32GB?
On the models both run fully in memory, the Framework Desktop Ryzen AI Max+ 395 64GB is about 1.8× as fast as the Mac mini M4 32GB (estimated, median across models).
What is the price difference between the Framework Desktop Ryzen AI Max+ 395 64GB and the Mac mini M4 32GB?
In the US the Framework Desktop Ryzen AI Max+ 395 64GB costs $1,899 at eBay (used) and the Mac mini M4 32GB $1,420 at eBay: the Mac mini M4 32GB is $479 cheaper.

More comparisons