readygpu

Mac mini M4 32GB vs NVIDIA RTX PRO 2000 Blackwell

For running models locally, priced in the US. At 8k context the first runs 59 models fully in memory, the second 44.

In short

The Mac mini M4 32GB has more memory for models: 32 GB against 16 GB. At 8k context the Mac mini M4 32GB runs 59 of the models we track fully in memory and the NVIDIA RTX PRO 2000 Blackwell 44; only the Mac mini M4 32GB holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA RTX PRO 2000 Blackwell is about 2.3× as fast as the Mac mini M4 32GB (estimated, median across models). In the US the Mac mini M4 32GB costs $1,330 at eBay and the NVIDIA RTX PRO 2000 Blackwell $1,580 at eBay: the Mac mini M4 32GB is $250 cheaper.

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

Mac mini M4 32GB

$1,330

eBay

Add to build
NVIDIA RTX PRO 2000 Blackwell

$1,580

eBay

Add to build

Specifications

SpecMac mini M4 32GBNVIDIA RTX PRO 2000 Blackwell
ChipApple M4 (10-core GPU)–
Memory bus128-bit128-bit
Memory bandwidth120 GB/s288 GB/s
FP16 compute3.76 TFLOPS17.03 TFLOPS
SoftwareMetalCUDA
Unified memory32 GB–
GPU can use by default21.3 GB–
GPU can use, tuned24 GB–
Operating systemmacos–
ProcessorM4 10-core–
Storage512 GB–
GPU–RTX PRO 2000 Blackwell
Memory–16 GB GDDR7
Board power–70 W
PCIe generation–Gen 5
PCIe lanes–x8

What each runs

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

ModelMac mini M4 32GBNVIDIA RTX PRO 2000 Blackwell
Qwen 3.8 27B4tok/sQ5_K_Moffload
Qwen 3.6 27B4tok/sQ5_K_Moffload
Gemma 4 31B4tok/sQ4_K_Moffload
Qwen 3.6 35B-A3B23tok/sMXFP4offload
Qwen 3.5 27B4tok/sQ5_K_Moffload
Gemma 4 26B-A4B13tok/sUD-Q5_K_Moffload
GLM 4.7 Flash12tok/sQ5_K_Moffload
Devstral Small 2 24B4tok/sQ6_K11tok/sQ4_K_M
Qwen3 Coder 30B-A3B18tok/sQ4_K_Moffload
gpt-oss 20B18tok/sMXFP441tok/sMXFP4
Qwen3 32B4tok/sQ4_K_Moffload
Gemma 4 12B6tok/sQ8_014tok/sQ8_0
Qwen 3.5 9B8tok/sQ8_018tok/sQ8_0
Gemma 3 27B4tok/sQ5_K_Moffload
Mistral Small 3.2 24B4tok/sQ6_K11tok/sQ4_K_M
DeepSeek R1 Distill Qwen 32B4tok/sQ4_K_Moffload
Ministral 3 14B5tok/sQ8_011tok/sQ8_0
Qwen3 14B5tok/sQ8_013tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B8tok/sQ8_018tok/sQ8_0
Qwen3 8B8tok/sQ8_018tok/sQ8_0
Phi-4 14B5tok/sQ8_013tok/sQ6_K
Qwen 3.5 4B16tok/sQ8_037tok/sQ8_0
Ministral 3 8B8tok/sQ8_018tok/sQ8_0
Granite 4.2 8B7tok/sQ8_017tok/sQ8_0
Gemma 4 E4B9tok/sQ8_021tok/sQ8_0
LFM2.5 8B-A1B32tok/sQ8_073tok/sQ8_0
Llama 3.1 8B10tok/sQ6_K23tok/sQ6_K
Qwen2.5 0.5B124tok/sQ8_0283tok/sQ8_0
Qwen3.5 0.8B84tok/sQ8_0192tok/sQ8_0
Qwen3.5 2B50tok/sQ5_K_M115tok/sQ5_K_M
LFM3 1.7B40tok/sQ8_091tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B37tok/sQ8_084tok/sQ8_0
MiniCPM5 2B26tok/sQ8_059tok/sQ8_0
LFM2.5 2.6B23tok/sQ8_053tok/sQ8_0
LFM2.5 VL 3B23tok/sQ8_053tok/sQ8_0
Spark X2.5 4B23tok/smlx-4bit53tok/smlx-4bit
LFM2.5 24B A2B19tok/sQ6_Koffload
granite vision 4.1 4b18tok/sQ8_042tok/sQ8_0
Ministral 3 3B Instruct 251217tok/sQ8_040tok/sQ8_0
granite 4.2 3b17tok/sQ8_039tok/sQ8_0
Mellum2.1 12B A2.5B Thinking17tok/sQ8_038tok/sQ8_0
FrogNano 4B 260916tok/sQ8_036tok/sQ8_0
Kimi VL A3B Thinking 250614tok/sQ8_049tok/sQ4_K_M
Kimi VL A3B13tok/smlx-8bit39tok/smlx-6bit
DeepSeek R1 Distill Qwen 7B9tok/sQ8_021tok/sQ8_0
GLM 4 9B 04149tok/smlx-5bit21tok/smlx-5bit
DeepSeek R1 Distill Llama 8B8tok/sQ8_019tok/sQ8_0
Ministral 3 8B Reasoning 25128tok/sQ8_018tok/sQ8_0
GLM 4.6V Flash8tok/sQ8_017tok/sQ8_0
GLM 4.1V 9B Thinking6tok/smlx-8bit15tok/smlx-8bit
Ministral 3 14B Reasoning 25125tok/sQ8_011tok/sQ8_0
DeepSeek R1 Distill Qwen 14B5tok/sQ8_013tok/sQ6_K
Devstral Small 25074tok/sQ5_K_M11tok/sQ4_K_M
Magistral Small 25074tok/sQ5_K_M11tok/sQ4_K_M
Magistral Small 25094tok/sQ5_K_M11tok/sQ4_K_M
granite 4.2 30b4tok/sQ4_K_Moffload
Magistral Small 25064tok/sQ6_K11tok/sQ4_K_M
Muse Glimmer 30B4tok/sQ5_K_Moffload
Qwen3.8 27B OBLITERATED4tok/smlx-4bitoffload
Qwen 3.5 122B-A10Bwon't runoffload
Mistral Small 4 119Bwon't runoffload
Qwen 3.5 35B-A3Bwon't runoffload
Nemotron 3.5 Lightning 30B-A3Bwon't runoffload
Kimi Linear 48B-A3Bwon'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
Nemotron 3 Super 120B-A12Bwon't runwon't run
Qwen3 Coder Nextwon't runwon't run
gpt-oss 120Bwon't runwon't run
GLM 4.5 Airwon't runwon't run
Qwen3 Next 80B-A3Bwon't runwon't run
Llama 3.3 70Bwon't runwon't run
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek R1 Distill Llama 70Bwon'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 32GB or the NVIDIA RTX PRO 2000 Blackwell?
Choose the Mac mini M4 32GB to run bigger models. Choose the NVIDIA RTX PRO 2000 Blackwell for speed. Choose the Mac mini M4 32GB to spend less.
Which can run bigger models, the Mac mini M4 32GB or the NVIDIA RTX PRO 2000 Blackwell?
At 8k context the Mac mini M4 32GB runs 59 of the models we track fully in memory and the NVIDIA RTX PRO 2000 Blackwell 44; only the Mac mini M4 32GB holds Qwen 3.8 27B.
Which is faster for local AI, the Mac mini M4 32GB or the NVIDIA RTX PRO 2000 Blackwell?
On the models both run fully in memory, the NVIDIA RTX PRO 2000 Blackwell is about 2.3× as fast as the Mac mini M4 32GB (estimated, median across models).
What is the price difference between the Mac mini M4 32GB and the NVIDIA RTX PRO 2000 Blackwell?
In the US the Mac mini M4 32GB costs $1,330 at eBay and the NVIDIA RTX PRO 2000 Blackwell $1,580 at eBay: the Mac mini M4 32GB is $250 cheaper.

More comparisons

More hardware for local AI