← AI Hashrate

Mac mini M4 32GB vs RTX 4090D 24GB (China) for Local LLMs

The RTX 4090D 24GB (China) has about 740% more memory bandwidth (1,008 vs 120 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 740% faster on the RTX 4090D 24GB (China). The Mac mini M4 32GB fits more of the catalog at Q4/8K — 38 vs 33 of 61 models (32 vs 24 GB VRAM). Largest model that fits the Mac mini M4 32GB but not the RTX 4090D 24GB (China): Mixtral-8x7B-Instruct-v0.1 (46.7B). MSRP is $999 for the Mac mini M4 32GB vs $1,599 for the RTX 4090D 24GB (China). MSRP is a launch list price, not live retail — Amazon prices move; click through for the current price. Not retail-shoppable: RTX 4090D 24GB (China) (datacenter-class; cloud rental is the realistic way to use it). In the Q4/8K head-to-head below (47 shared models), the RTX 4090D 24GB (China) posts the higher tok/s in 47 rows vs 0. Methodology.

Spec comparison

Mac mini M4 32GBRTX 4090D 24GB (China)
VendorAppleNVIDIA
VRAM32 GB24 GB
Memory typeLPDDR5XGDDR6X
Memory bandwidth120 GB/s1,008 GB/s
TDP155 W425 W
MSRP (list)$999$1,599
BuySearch Amazon (affiliate)—

MSRP is the launch list price, not live retail. Buy links are Amazon affiliate links — the price after you click is the live price.

Q4 / 8K head-to-head — top 15 of 47 shared models

ModelParams (B)Mac mini M4 32GB tok/sMac mini M4 32GB fitsRTX 4090D 24GB (China) tok/sRTX 4090D 24GB (China) fitsWinner
Qwen3-0.6B0.895.5 est.Yes801.8 est.YesRTX 4090D 24GB (China)
gemma-3-1b-it1.076.4 est.Yes641.5 est.YesRTX 4090D 24GB (China)
Llama-3.2-1B-Instruct1.263.6 est.Yes534.5 est.YesRTX 4090D 24GB (China)
Qwen3-1.7B2.038.2 est.Yes320.7 est.YesRTX 4090D 24GB (China)
Qwen3-30B-A3B30.525.5 est.Yes213.8 est.YesRTX 4090D 24GB (China)
Qwen3-Coder-30B-A3B-Instruct30.525.5 est.Yes213.8 est.YesRTX 4090D 24GB (China)
GLM-4.7-Flash31.225.5 est.Yes213.8 est.YesRTX 4090D 24GB (China)
Qwen3-30B-A3B-Instruct-250730.525.5 est.Yes213.8 est.YesRTX 4090D 24GB (China)
Llama-3.2-3B-Instruct3.241.3 measuredYes200.5 est.YesRTX 4090D 24GB (China)
gpt-oss-20b21.521.2 est.Yes178.2 est.YesRTX 4090D 24GB (China)
Qwen3-Coder-Next79.736.1 est.No170.4 est.NoRTX 4090D 24GB (China)
Phi-4-mini-instruct3.820.1 est.Yes168.8 est.YesRTX 4090D 24GB (China)
Phi-4-mini-reasoning3.820.1 est.Yes168.8 est.YesRTX 4090D 24GB (China)
gemma-3-4b-it4.319.6 est.Yes164.5 est.YesRTX 4090D 24GB (China)
Qwen3-Next-80B-A3B-Instruct81.334.7 est.No164.0 est.NoRTX 4090D 24GB (China)

est. = bandwidth-based estimate; measured = curated real benchmark that overrides the estimate. Fits = weights + KV(8K) + 1 GB overhead ≤ 95% of VRAM.

Fit coverage at Q4 / 8K

Mac mini M4 32GBRTX 4090D 24GB (China)
Catalog models that fit38 of 6133 of 61
Largest exclusive fitMixtral-8x7B-Instruct-v0.1 (46.7B)—

Mac mini M4 32GB details → · RTX 4090D 24GB (China) details →