readygpu

Mac mini M4 Pro 64GB vs AMD Radeon PRO W7900

For running models locally, priced in the US. At 64k context the first runs 66 models fully in memory, the second 64.

In short

The Mac mini M4 Pro 64GB has more memory for models: 64 GB against 48 GB. At 64k context the Mac mini M4 Pro 64GB runs 66 of the models we track fully in memory and the AMD Radeon PRO W7900 64; only the Mac mini M4 Pro 64GB holds Qwen3 Coder Next. On the models both run fully in memory, the AMD Radeon PRO W7900 is about 2.7× as fast as the Mac mini M4 Pro 64GB (estimated, median across models). In the US the Mac mini M4 Pro 64GB costs $3,299 at eBay and the AMD Radeon PRO W7900 $4,000 at eBay: the Mac mini M4 Pro 64GB is $701 cheaper.

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

Mac mini M4 Pro 64GB

$3,299

eBay

Add to build
AMD Radeon PRO W7900

$4,000

eBay

Add to build

Specifications

SpecMac mini M4 Pro 64GBAMD Radeon PRO W7900
ChipApple M4 Pro (20-core GPU)–
Memory bus256-bit384-bit
Memory bandwidth273 GB/s864 GB/s
FP16 compute8.08 TFLOPS122.6 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 PRO W7900
Memory–48 GB GDDR6
Board power–295 W
PCIe generation–Gen 4
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 PRO W7900
Qwen 3.8 27B5tok/sQ8_014tok/sQ8_0
Qwen 3.5 122B-A10B21tok/sUD-Q2_K_XL56tok/sUD-Q2_K_XL
Qwen 3.6 27B5tok/sQ8_014tok/sQ8_0
Qwen3 Coder Next26tok/sQ4_K_Moffload
Gemma 4 31B5tok/sQ8_012tok/sQ8_0
Mistral Small 4 119B27tok/sUD-Q2_K_XL73tok/sUD-Q2_K_XL
Qwen 3.6 35B-A3B24tok/sQ8_064tok/sQ8_0
Qwen 3.5 27B5tok/sQ8_014tok/sQ8_0
Gemma 4 26B-A4B19tok/sQ8_050tok/sQ8_0
Qwen3 Next 80B-A3B31tok/sQ4_K_Moffload
Qwen 3.5 35B-A3B24tok/sQ8_064tok/sQ8_0
GLM 4.7 Flash12tok/sQ8_032tok/sQ8_0
Devstral Small 2 24B5tok/sQ8_013tok/sQ8_0
Nemotron 3.5 Lightning 30B-A3B28tok/sUD-Q6_K_XL76tok/sUD-Q6_K_XL
Kimi Linear 48B-A3B35tok/sQ6_K94tok/sQ6_K
gpt-oss 20B26tok/sMXFP471tok/sMXFP4
Qwen3 Coder 30B-A3B11tok/sQ8_030tok/sQ8_0
Qwen3 32B4tok/sQ6_K11tok/sQ6_K
Gemma 4 12B13tok/sQ8_034tok/sQ8_0
Qwen 3.5 9B15tok/sQ8_041tok/sQ8_0
Gemma 3 27B5tok/sQ8_014tok/sQ8_0
Mistral Small 3.2 24B5tok/sQ8_013tok/sQ8_0
DeepSeek R1 Distill Qwen 32B4tok/sQ6_K11tok/sQ6_K
Ministral 3 14B7tok/sQ8_019tok/sQ8_0
Qwen3 14B7tok/sQ8_018tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B10tok/sQ8_026tok/sQ8_0
Qwen3 8B10tok/sQ8_026tok/sQ8_0
Phi-4 14B6tok/sQ8_016tok/sQ8_0
Qwen 3.5 4B27tok/sQ8_071tok/sQ8_0
Ministral 3 8B10tok/sQ8_026tok/sQ8_0
Granite 4.2 8B9tok/sQ8_024tok/sQ8_0
Gemma 4 E4B18tok/sQ8_047tok/sQ8_0
LFM2.5 8B-A1B25tok/sQ8_067tok/sQ8_0
Llama 3.1 8B12tok/sQ6_K31tok/sQ6_K
Qwen2.5 0.5B133tok/sQ8_0356tok/sQ8_0
Qwen3.5 0.8B109tok/sQ8_0291tok/sQ8_0
Qwen3.5 2B79tok/sQ5_K_M210tok/sQ5_K_M
LFM3 1.7B67tok/sQ8_0179tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B47tok/sQ8_0126tok/sQ8_0
MiniCPM5 2B32tok/sQ8_086tok/sQ8_0
Spark X2.5 4B32tok/smlx-4bit86tok/smlx-4bit
Mellum2.1 12B A2.5B Thinking29tok/sQ8_078tok/sQ8_0
FrogNano 4B 260926tok/sQ8_070tok/sQ8_0
LFM2.5 2.6B26tok/sQ8_069tok/sQ8_0
LFM2.5 VL 3B26tok/sQ8_069tok/sQ8_0
Kimi VL A3B Thinking 250621tok/sQ8_055tok/sQ8_0
Kimi VL A3B20tok/smlx-8bit54tok/smlx-8bit
granite vision 4.1 4b20tok/sQ8_053tok/sQ8_0
granite 4.2 3b19tok/sQ8_051tok/sQ8_0
Ministral 3 3B Instruct 251217tok/sQ8_045tok/sQ8_0
GLM 4 9B 041416tok/smlx-5bit44tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B15tok/sQ8_040tok/sQ8_0
LFM2.5 24B A2B14tok/sQ8_038tok/sQ8_0
GLM 4.6V Flash14tok/sQ8_038tok/sQ8_0
GLM 4.1V 9B Thinking12tok/smlx-8bit33tok/smlx-8bit
DeepSeek R1 Distill Llama 8B10tok/sQ8_028tok/sQ8_0
Ministral 3 8B Reasoning 251210tok/sQ8_026tok/sQ8_0
Ministral 3 14B Reasoning 25127tok/sQ8_019tok/sQ8_0
Qwen3.8 27B OBLITERATED7tok/smlx-4bit19tok/smlx-4bit
DeepSeek R1 Distill Qwen 14B6tok/sQ8_017tok/sQ8_0
Muse Glimmer 30B5tok/sQ8_014tok/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_010tok/sQ8_0
Nemotron 3 Super 120B-A12Bwon't runoffload
gpt-oss 120Bwon't runoffload
GLM 4.5 Airwon't runoffload
Llama 3.3 70Bwon't runoffload
DeepSeek R1 Distill Llama 70Bwon't runoffload
GLM 4.5Vwon'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
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 4.6Vwon'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 PRO W7900?
Choose the Mac mini M4 Pro 64GB to run bigger models. Choose the AMD Radeon PRO W7900 for speed. Choose the Mac mini M4 Pro 64GB to spend less.
Which can run bigger models, the Mac mini M4 Pro 64GB or the AMD Radeon PRO W7900?
At 64k context the Mac mini M4 Pro 64GB runs 66 of the models we track fully in memory and the AMD Radeon PRO W7900 64; only the Mac mini M4 Pro 64GB holds Qwen3 Coder Next.
Which is faster for local AI, the Mac mini M4 Pro 64GB or the AMD Radeon PRO W7900?
On the models both run fully in memory, the AMD Radeon PRO W7900 is about 2.7× 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 PRO W7900?
In the US the Mac mini M4 Pro 64GB costs $3,299 at eBay and the AMD Radeon PRO W7900 $4,000 at eBay: the Mac mini M4 Pro 64GB is $701 cheaper.

More comparisons

More hardware for local AI