readygpu

Mac mini M4 32GB vs NVIDIA Tesla P40

For running models locally, priced in the UK. At 8k context the first runs 54 models fully in memory, the second 56.

In short

The Mac mini M4 32GB has more memory for models: 32 GB against 24 GB. At 8k context the NVIDIA Tesla P40 runs 56 of the models we track fully in memory and the Mac mini M4 32GB 54; only the NVIDIA Tesla P40 holds Qwen 3.5 35B-A3B. On the models both run fully in memory, the NVIDIA Tesla P40 is about 2.7× as fast as the Mac mini M4 32GB (estimated, median across models). In the UK the Mac mini M4 32GB costs £1,899 at eBay (used) and the NVIDIA Tesla P40 £261 at eBay (used): the NVIDIA Tesla P40 is £1,638 cheaper.

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

Mac mini M4 32GB

£1,899

eBay, used (asking)

Add to build
NVIDIA Tesla P40

£234

eBay

Add to build

Specifications

SpecMac mini M4 32GBNVIDIA Tesla P40
ChipApple M4 (10-core GPU)–
Memory bus128-bit384-bit
Memory bandwidth120 GB/s346 GB/s
FP16 compute3.76 TFLOPS11.8 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–Tesla P40
Memory–24 GB GDDR5
Board power–250 W
PCIe generation–Gen 3
PCIe lanes–x16

What each runs

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

ModelMac mini M4 32GBNVIDIA Tesla P40
Qwen 3.8 27B4tok/sQ5_K_M10tok/sUD-Q6_K
Qwen 3.6 27B4tok/sQ5_K_M9tok/sQ6_K
Gemma 4 31B4tok/sQ4_K_M9tok/sQ5_K_M
Qwen 3.6 35B-A3B23tok/sMXFP462tok/sQ4_K_M
Qwen 3.5 27B4tok/sQ5_K_M9tok/sQ6_K
Gemma 4 26B-A4B13tok/sUD-Q5_K_M32tok/sUD-Q6_K
GLM 4.7 Flash12tok/sQ5_K_M32tok/sQ5_K_M
Devstral Small 2 24B4tok/sQ6_K10tok/sQ6_K
Qwen 3.5 35B-A3Bwon't run62tok/sQ4_K_M
Nemotron 3.5 Lightning 30B-A3Bwon't run56tok/sMXFP4
Qwen3 Coder 30B-A3B18tok/sQ4_K_M44tok/sQ5_K_M
gpt-oss 20B18tok/sMXFP449tok/sMXFP4
Qwen3 32B4tok/sQ4_K_M10tok/sQ4_K_M
Gemma 4 12B6tok/sQ8_016tok/sQ8_0
Qwen 3.5 9B8tok/sQ8_022tok/sQ8_0
Gemma 3 27B4tok/sQ5_K_M9tok/sQ6_K
Mistral Small 3.2 24B4tok/sQ6_K10tok/sQ6_K
DeepSeek R1 Distill Qwen 32B4tok/sQ4_K_M10tok/sQ4_K_M
Ministral 3 14B5tok/sQ8_014tok/sQ8_0
Qwen3 14B5tok/sQ8_013tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B8tok/sQ8_022tok/sQ8_0
Qwen3 8B8tok/sQ8_022tok/sQ8_0
Phi-4 14B5tok/sQ8_012tok/sQ8_0
Qwen 3.5 4B16tok/sQ8_045tok/sQ8_0
Ministral 3 8B8tok/sQ8_021tok/sQ8_0
Granite 4.2 8B7tok/sQ8_020tok/sQ8_0
Gemma 4 E4B9tok/sQ8_025tok/sQ8_0
LFM2.5 8B-A1B32tok/sQ8_088tok/sQ8_0
Llama 3.1 8B10tok/sQ6_K28tok/sQ6_K
Qwen2.5 0.5B124tok/sQ8_0340tok/sQ8_0
Qwen3.5 0.8B84tok/sQ8_0230tok/sQ8_0
Qwen3.5 2B50tok/sQ5_K_M138tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B37tok/sQ8_0101tok/sQ8_0
MiniCPM5 2B26tok/sQ8_071tok/sQ8_0
LFM2.5 2.6B23tok/sQ8_064tok/sQ8_0
LFM2.5 VL 3B23tok/sQ8_064tok/sQ8_0
Spark X2.5 4B23tok/smlx-4bit63tok/smlx-4bit
LFM2.5 24B A2B19tok/sQ6_K53tok/sQ6_K
granite vision 4.1 4b18tok/sQ8_050tok/sQ8_0
granite 4.2 3b17tok/sQ8_047tok/sQ8_0
Mellum2.1 12B A2.5B Thinking17tok/sQ8_046tok/sQ8_0
Kimi VL A3B Thinking 250614tok/sQ8_038tok/sQ8_0
Kimi VL A3B13tok/smlx-8bit37tok/smlx-8bit
DeepSeek R1 Distill Qwen 7B9tok/sQ8_025tok/sQ8_0
GLM 4 9B 04149tok/smlx-5bit25tok/smlx-5bit
DeepSeek R1 Distill Llama 8B8tok/sQ8_022tok/sQ8_0
Ministral 3 8B Reasoning 25128tok/sQ8_021tok/sQ8_0
GLM 4.6V Flash8tok/sQ8_021tok/sQ8_0
GLM 4.1V 9B Thinking6tok/smlx-8bit18tok/smlx-8bit
DeepSeek R1 Distill Qwen 14B5tok/sQ8_012tok/sQ8_0
Devstral Small 25074tok/sQ5_K_M12tok/sQ5_K_M
Magistral Small 25074tok/sQ5_K_M12tok/sQ5_K_M
Magistral Small 25094tok/sQ5_K_M12tok/sQ5_K_M
granite 4.2 30b4tok/sQ4_K_M9tok/sQ5_K_M
Magistral Small 25064tok/sQ6_K10tok/sQ6_K
Qwen3.8 27B OBLITERATED4tok/smlx-4bit10tok/smlx-4bit
Qwen 3.5 122B-A10Bwon't runoffload
Qwen3 Coder Nextwon't runoffload
Mistral Small 4 119Bwon't runoffload
GLM 4.5 Airwon't runoffload
Qwen3 Next 80B-A3Bwon't runoffload
Kimi Linear 48B-A3Bwon't runoffload
Llama 3.3 70Bwon't runoffload
DeepSeek R1 Distill Llama 70Bwon'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
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 Mac mini M4 32GB or the NVIDIA Tesla P40?
Choose the NVIDIA Tesla P40 to run bigger models. Choose the NVIDIA Tesla P40 for speed. Choose the NVIDIA Tesla P40 to spend less.
Which can run bigger models, the Mac mini M4 32GB or the NVIDIA Tesla P40?
At 8k context the NVIDIA Tesla P40 runs 56 of the models we track fully in memory and the Mac mini M4 32GB 54; only the NVIDIA Tesla P40 holds Qwen 3.5 35B-A3B.
Which is faster for local AI, the Mac mini M4 32GB or the NVIDIA Tesla P40?
On the models both run fully in memory, the NVIDIA Tesla P40 is about 2.7× 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 Tesla P40?
In the UK the Mac mini M4 32GB costs £1,899 at eBay (used) and the NVIDIA Tesla P40 £261 at eBay (used): the NVIDIA Tesla P40 is £1,638 cheaper.

More comparisons