readygpu

Mac mini M4 Pro 64GB vs AMD Radeon AI PRO R9700

For running models locally, priced in the US. At 8k context the first runs 65 models fully in memory, the second 58.

In short

The Mac mini M4 Pro 64GB has more memory for models: 64 GB against 32 GB. At 8k context the Mac mini M4 Pro 64GB runs 65 of the models we track fully in memory and the AMD Radeon AI PRO R9700 58; only the Mac mini M4 Pro 64GB holds Qwen 3.5 122B-A10B. On the models both run fully in memory, the AMD Radeon AI PRO R9700 is about 2.0× as fast as the Mac mini M4 Pro 64GB (estimated, median across models). In the US the Mac mini M4 Pro 64GB costs $2,600 at eBay and the AMD Radeon AI PRO R9700 $1,900 at Amazon: the AMD Radeon AI PRO R9700 is $700 cheaper.

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

Mac mini M4 Pro 64GB

$2,600

eBay

Add to build
AMD Radeon AI PRO R9700

$1,900

Amazon

Add to build

Specifications

SpecMac mini M4 Pro 64GBAMD Radeon AI PRO R9700
ChipApple M4 Pro (20-core GPU)–
Memory bus256-bit256-bit
Memory bandwidth273 GB/s640 GB/s
FP16 compute8.08 TFLOPS191 TFLOPS
SoftwareMetalROCm
Unified memory64 GB–
GPU can use by default48 GB–
GPU can use, tuned56 GB–
Operating systemmacos–
ProcessorM4 Pro 14-core–
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.

ModelMac mini M4 Pro 64GBAMD Radeon AI PRO R9700
Qwen 3.8 27B6tok/sQ8_012tok/sQ8_0
Qwen 3.5 122B-A10B29tok/sUD-Q2_K_XLoffload
Qwen 3.6 27B6tok/sQ8_012tok/sQ8_0
Qwen3 Coder Next40tok/sQ4_K_Moffload
Gemma 4 31B5tok/sQ8_013tok/sQ6_K
Mistral Small 4 119B42tok/sUD-Q2_K_XLoffload
Qwen 3.6 35B-A3B32tok/sQ8_075tok/sQ6_K
Qwen 3.5 27B6tok/sQ8_012tok/sQ8_0
Gemma 4 26B-A4B23tok/sQ8_047tok/sQ8_0
GLM 4.5 Air15tok/sQ2_Koffload
Qwen3 Next 80B-A3B52tok/sQ4_K_Moffload
Qwen 3.5 35B-A3B32tok/sQ8_080tok/sQ6_K
GLM 4.7 Flash19tok/sQ8_037tok/sQ8_0
Devstral Small 2 24B7tok/sQ8_013tok/sQ8_0
Nemotron 3.5 Lightning 30B-A3B31tok/sUD-Q6_K_XL71tok/sUD-Q5_K_M
Kimi Linear 48B-A3B41tok/sQ6_K109tok/sQ4_K_M
gpt-oss 20B40tok/sMXFP480tok/sMXFP4
Qwen3 Coder 30B-A3B27tok/sQ8_065tok/sQ6_K
Qwen3 32B5tok/sQ8_012tok/sQ6_K
Gemma 4 12B14tok/sQ8_027tok/sQ8_0
Qwen 3.5 9B18tok/sQ8_036tok/sQ8_0
Mistral Small 3.2 24B7tok/sQ8_013tok/sQ8_0
Gemma 3 27B6tok/sQ8_012tok/sQ8_0
DeepSeek R1 Distill Qwen 32B5tok/sQ8_012tok/sQ6_K
Llama 3.3 70B4tok/sQ4_K_Moffload
Ministral 3 14B11tok/sQ8_022tok/sQ8_0
Qwen3 14B10tok/sQ8_021tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B18tok/sQ8_036tok/sQ8_0
Qwen3 8B18tok/sQ8_036tok/sQ8_0
Phi-4 14B10tok/sQ8_020tok/sQ8_0
Qwen 3.5 4B37tok/sQ8_073tok/sQ8_0
Ministral 3 8B17tok/sQ8_035tok/sQ8_0
Granite 4.2 8B17tok/sQ8_033tok/sQ8_0
Gemma 4 E4B21tok/sQ8_042tok/sQ8_0
LFM2.5 8B-A1B73tok/sQ8_0144tok/sQ8_0
Llama 3.1 8B23tok/sQ6_K46tok/sQ6_K
Qwen2.5 0.5B281tok/sQ8_0557tok/sQ8_0
Qwen3.5 0.8B191tok/sQ8_0378tok/sQ8_0
Qwen3.5 2B114tok/sQ5_K_M226tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B83tok/sQ8_0165tok/sQ8_0
MiniCPM5 2B59tok/sQ8_0116tok/sQ8_0
LFM2.5 2.6B53tok/sQ8_0104tok/sQ8_0
LFM2.5 VL 3B53tok/sQ8_0104tok/sQ8_0
Spark X2.5 4B52tok/smlx-4bit104tok/smlx-4bit
granite vision 4.1 4b41tok/sQ8_082tok/sQ8_0
granite 4.2 3b39tok/sQ8_077tok/sQ8_0
LFM2.5 24B A2B38tok/sQ8_076tok/sQ8_0
Mellum2.1 12B A2.5B Thinking38tok/sQ8_075tok/sQ8_0
FrogNano 4B 260936tok/sQ8_071tok/sQ8_0
Kimi VL A3B Thinking 250632tok/sQ8_063tok/sQ8_0
Kimi VL A3B30tok/smlx-8bit60tok/smlx-8bit
DeepSeek R1 Distill Qwen 7B21tok/sQ8_041tok/sQ8_0
GLM 4 9B 041421tok/smlx-5bit41tok/smlx-5bit
DeepSeek R1 Distill Llama 8B19tok/sQ8_037tok/sQ8_0
Ministral 3 8B Reasoning 251217tok/sQ8_035tok/sQ8_0
GLM 4.6V Flash17tok/sQ8_034tok/sQ8_0
GLM 4.1V 9B Thinking15tok/smlx-8bit29tok/smlx-8bit
DeepSeek R1 Distill Qwen 14B10tok/sQ8_020tok/sQ8_0
Qwen3.8 27B OBLITERATED8tok/smlx-4bit17tok/smlx-4bit
Devstral Small 25077tok/sQ8_013tok/sQ8_0
Magistral Small 25067tok/sQ8_013tok/sQ8_0
Magistral Small 25077tok/sQ8_013tok/sQ8_0
Magistral Small 25097tok/sQ8_013tok/sQ8_0
granite 4.2 30b5tok/sQ8_013tok/sQ6_K
DeepSeek R1 Distill Llama 70B4tok/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 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 4.5Vwon'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 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 Mac mini M4 Pro 64GB or the AMD Radeon AI PRO R9700?
Choose the Mac mini M4 Pro 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 Mac mini M4 Pro 64GB or the AMD Radeon AI PRO R9700?
At 8k context the Mac mini M4 Pro 64GB runs 65 of the models we track fully in memory and the AMD Radeon AI PRO R9700 58; only the Mac mini M4 Pro 64GB holds Qwen 3.5 122B-A10B.
Which is faster for local AI, the Mac mini M4 Pro 64GB or the AMD Radeon AI PRO R9700?
On the models both run fully in memory, the AMD Radeon AI PRO R9700 is about 2.0× as fast as the Mac mini M4 Pro 64GB (estimated, median across models).
What is the price difference between the Mac mini M4 Pro 64GB and the AMD Radeon AI PRO R9700?
In the US the Mac mini M4 Pro 64GB costs $2,600 at eBay and the AMD Radeon AI PRO R9700 $1,900 at Amazon: the AMD Radeon AI PRO R9700 is $700 cheaper.

More comparisons