readygpu

Mac mini M4 16GB vs AMD Radeon RX 7900 XTX

For running models locally, priced in the UK. At 8k context the first runs 28 models fully in memory, the second 53.

In short

The AMD Radeon RX 7900 XTX has more memory for models: 24 GB against 16 GB. At 8k context the AMD Radeon RX 7900 XTX runs 53 of the models we track fully in memory and the Mac mini M4 16GB 28; only the AMD Radeon RX 7900 XTX holds Qwen 3.8 27B. On the models both run fully in memory, the AMD Radeon RX 7900 XTX is about 6.8× as fast as the Mac mini M4 16GB (estimated, median across models). In the UK the Mac mini M4 16GB costs £799 at Amazon and the AMD Radeon RX 7900 XTX £999 at Amazon: the Mac mini M4 16GB is £200 cheaper.

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

Mac mini M4 16GB

£799

Amazon

Add to build
AMD Radeon RX 7900 XTX

£999

Amazon

Add to build

Specifications

SpecMac mini M4 16GBAMD Radeon RX 7900 XTX
ChipApple M4 (10-core GPU)–
Memory bus128-bit384-bit
Memory bandwidth120 GB/s960 GB/s
FP16 compute3.76 TFLOPS123 TFLOPS
SoftwareMetalROCm
Unified memory16 GB–
GPU can use by default10.7 GB–
GPU can use, tuned10.666666666666666 GB–
Operating systemmacos–
ProcessorM4 10-core–
Storage256 GB–
GPU–Radeon RX 7900 XTX
Memory–24 GB GDDR6
Board power–355 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 16GBAMD Radeon RX 7900 XTX
Qwen 3.8 27Bwon't run23tok/sUD-Q6_K
Qwen 3.6 27Bwon't run23tok/sQ6_K
Gemma 4 31Bwon't run23tok/sQ5_K_M
Qwen 3.5 27Bwon't run23tok/sQ6_K
Qwen 3.6 35B-A3Bwon't run152tok/sQ4_K_M
Gemma 4 26B-A4Bwon't run80tok/sUD-Q6_K
Devstral Small 2 24Bwon't run26tok/sQ6_K
GLM 4.7 Flashwon't run79tok/sQ5_K_M
Qwen 3.5 35B-A3Bwon't run153tok/sQ4_K_M
Qwen3 Coder 30B-A3Bwon't run108tok/sQ5_K_M
gpt-oss 20Bwon't run120tok/sMXFP4
Qwen3 32Bwon't run24tok/sQ4_K_M
Gemma 4 12B8tok/sQ6_K40tok/sQ8_0
Qwen 3.5 9B8tok/sQ8_054tok/sQ8_0
DeepSeek R1 Distill Qwen 32Bwon't run24tok/sQ4_K_M
Gemma 3 27Bwon't run23tok/sQ6_K
Mistral Small 3.2 24Bwon't run26tok/sQ6_K
Ministral 3 14B8tok/sQ4_K_M34tok/sQ8_0
Qwen3 14B8tok/sQ4_K_M31tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B8tok/sQ8_053tok/sQ8_0
Qwen3 8B8tok/sQ8_053tok/sQ8_0
Phi-4 14B7tok/sQ4_K_M31tok/sQ8_0
Qwen 3.5 4B16tok/sQ8_0110tok/sQ8_0
Ministral 3 8B8tok/sQ8_052tok/sQ8_0
Granite 4.2 8B7tok/sQ8_049tok/sQ8_0
Gemma 4 E4B9tok/sQ8_062tok/sQ8_0
LFM2.5 8B-A1B32tok/sQ8_0216tok/sQ8_0
Llama 3.1 8B10tok/sQ6_K69tok/sQ6_K
Qwen2.5 0.5B124tok/sQ8_0836tok/sQ8_0
Qwen3.5 0.8B84tok/sQ8_0567tok/sQ8_0
Qwen3.5 2B50tok/sQ5_K_M340tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B37tok/sQ8_0248tok/sQ8_0
MiniCPM5 2B26tok/sQ8_0174tok/sQ8_0
LFM2.5 2.6B23tok/sQ8_0156tok/sQ8_0
LFM2.5 VL 3B23tok/sQ8_0156tok/sQ8_0
granite vision 4.1 4b18tok/sQ8_0123tok/sQ8_0
granite 4.2 3b17tok/sQ8_0116tok/sQ8_0
DeepSeek R1 Distill Qwen 7B9tok/sQ8_062tok/sQ8_0
GLM 4 9B 04149tok/smlx-5bit62tok/smlx-5bit
DeepSeek R1 Distill Llama 8B8tok/sQ8_055tok/sQ8_0
Ministral 3 8B Reasoning 25128tok/sQ8_052tok/sQ8_0
GLM 4.6V Flash8tok/sQ8_051tok/sQ8_0
DeepSeek R1 Distill Qwen 14B7tok/sQ4_K_M31tok/sQ8_0
Devstral Small 2507won't run29tok/sQ5_K_M
GLM 4.1V 9B Thinkingwon't run44tok/smlx-8bit
Kimi VL A3Bwon't run90tok/smlx-8bit
Kimi VL A3B Thinking 2506won't run94tok/sQ8_0
LFM2.5 24B A2Bwon't run130tok/sQ6_K
Magistral Small 2506won't run26tok/sQ6_K
Magistral Small 2507won't run29tok/sQ5_K_M
Magistral Small 2509won't run29tok/sQ5_K_M
Mellum2.1 12B A2.5B Thinkingwon't run112tok/sQ8_0
granite 4.2 30bwon't run23tok/sQ5_K_M
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
Nemotron 3.5 Lightning 30B-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 16GB or the AMD Radeon RX 7900 XTX?
Choose the AMD Radeon RX 7900 XTX to run bigger models. Choose the AMD Radeon RX 7900 XTX for speed. Choose the Mac mini M4 16GB to spend less.
Which can run bigger models, the Mac mini M4 16GB or the AMD Radeon RX 7900 XTX?
At 8k context the AMD Radeon RX 7900 XTX runs 53 of the models we track fully in memory and the Mac mini M4 16GB 28; only the AMD Radeon RX 7900 XTX holds Qwen 3.8 27B.
Which is faster for local AI, the Mac mini M4 16GB or the AMD Radeon RX 7900 XTX?
On the models both run fully in memory, the AMD Radeon RX 7900 XTX is about 6.8× as fast as the Mac mini M4 16GB (estimated, median across models).
What is the price difference between the Mac mini M4 16GB and the AMD Radeon RX 7900 XTX?
In the UK the Mac mini M4 16GB costs £799 at Amazon and the AMD Radeon RX 7900 XTX £999 at Amazon: the Mac mini M4 16GB is £200 cheaper.

More comparisons