← AI Hashrate

RTX 4090 24GB vs RTX 4090D 24GB (China) for Local LLMs

Both list the same memory bandwidth (1,008 GB/s), so per-token decode speed should be similar whenever a model fits both. Both fit the same number of catalog models at Q4/8K (33 of 61; 24 vs 24 GB VRAM). MSRP is $1,599 for the RTX 4090 24GB 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 4090 24GB posts the higher tok/s in 8 rows vs 3. Methodology.

Spec comparison

RTX 4090 24GBRTX 4090D 24GB (China)
VendorNVIDIANVIDIA
VRAM24 GB24 GB
Memory typeGDDR6XGDDR6X
Memory bandwidth1,008 GB/s1,008 GB/s
TDP450 W425 W
MSRP (list)$1,599$1,599
BuyGIGABYTE GeForce RTX 4090 Gaming OC 24GB (affiliate) · More listings—

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)RTX 4090 24GB tok/sRTX 4090 24GB fitsRTX 4090D 24GB (China) tok/sRTX 4090D 24GB (China) fitsWinner
Qwen3-0.6B0.8801.8 est.Yes801.8 est.YesTie
gemma-3-1b-it1.0641.5 est.Yes641.5 est.YesTie
Llama-3.2-1B-Instruct1.2534.5 est.Yes534.5 est.YesTie
Qwen3-1.7B2.0320.7 est.Yes320.7 est.YesTie
gpt-oss-20b21.5225.2 measuredYes178.2 est.YesRTX 4090 24GB
Qwen3-30B-A3B30.5213.8 est.Yes213.8 est.YesTie
Qwen3-Coder-30B-A3B-Instruct30.5213.8 est.Yes213.8 est.YesTie
GLM-4.7-Flash31.2213.8 est.Yes213.8 est.YesTie
Qwen3-30B-A3B-Instruct-250730.5213.8 est.Yes213.8 est.YesTie
Llama-3.2-3B-Instruct3.2200.5 est.Yes200.5 est.YesTie
Mistral-7B-Instruct-v0.37.2183.3 measuredYes89.1 est.YesRTX 4090 24GB
Qwen3-Coder-Next79.7170.4 est.No170.4 est.NoTie
Phi-4-mini-instruct3.8168.8 est.Yes168.8 est.YesTie
Phi-4-mini-reasoning3.8168.8 est.Yes168.8 est.YesTie
gemma-3-4b-it4.3164.5 est.Yes164.5 est.YesTie

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

RTX 4090 24GBRTX 4090D 24GB (China)
Catalog models that fit33 of 6133 of 61
Largest exclusive fit——

RTX 4090 24GB details → · RTX 4090D 24GB (China) details →