RTX 4070 Ti Super 16GB vs RTX 4090D 24GB (China) for Local LLMs

The RTX 4090D 24GB (China) has about 50% more memory bandwidth (1,008 vs 672 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 50% faster on the RTX 4090D 24GB (China). The RTX 4090D 24GB (China) fits more of the catalog at Q4/8K — 33 vs 25 of 61 models (24 vs 16 GB VRAM). Largest model that fits the RTX 4090D 24GB (China) but not the RTX 4070 Ti Super 16GB: GLM-4.7-Flash (31.2B). MSRP is $799 for the RTX 4070 Ti Super 16GB 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 (44 shared models), the RTX 4090D 24GB (China) posts the higher tok/s in 34 rows vs 10. Methodology.

Spec comparison

	RTX 4070 Ti Super 16GB	RTX 4090D 24GB (China)
Vendor	NVIDIA	NVIDIA
VRAM	16 GB	24 GB
Memory type	GDDR6X	GDDR6X
Memory bandwidth	672 GB/s	1,008 GB/s
TDP	285 W	425 W
MSRP (list)	$799	$1,599
Buy	Search 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 44 shared models

Model	Params (B)	RTX 4070 Ti Super 16GB tok/s	RTX 4070 Ti Super 16GB fits	RTX 4090D 24GB (China) tok/s	RTX 4090D 24GB (China) fits	Winner
Qwen3-0.6B	0.8	534.5 est.	Yes	801.8 est.	Yes	RTX 4090D 24GB (China)
gemma-3-1b-it	1.0	427.6 est.	Yes	641.5 est.	Yes	RTX 4090D 24GB (China)
Llama-3.2-1B-Instruct	1.2	356.4 est.	Yes	534.5 est.	Yes	RTX 4090D 24GB (China)
Qwen3-1.7B	2.0	213.8 est.	Yes	320.7 est.	Yes	RTX 4090D 24GB (China)
Qwen3-30B-A3B	30.5	308.6 est.	No	213.8 est.	Yes	RTX 4070 Ti Super 16GB
Qwen3-Coder-30B-A3B-Instruct	30.5	308.6 est.	No	213.8 est.	Yes	RTX 4070 Ti Super 16GB
Qwen3-30B-A3B-Instruct-2507	30.5	308.6 est.	No	213.8 est.	Yes	RTX 4070 Ti Super 16GB
GLM-4.7-Flash	31.2	296.3 est.	No	213.8 est.	Yes	RTX 4070 Ti Super 16GB
Llama-3.2-3B-Instruct	3.2	199.0 measured	Yes	200.5 est.	Yes	RTX 4090D 24GB (China)
gpt-oss-20b	21.5	118.8 est.	Yes	178.2 est.	Yes	RTX 4090D 24GB (China)
Qwen3-Coder-Next	79.7	50.5 est.	No	170.4 est.	No	RTX 4090D 24GB (China)
Phi-4-mini-instruct	3.8	112.5 est.	Yes	168.8 est.	Yes	RTX 4090D 24GB (China)
Phi-4-mini-reasoning	3.8	112.5 est.	Yes	168.8 est.	Yes	RTX 4090D 24GB (China)
gemma-3-4b-it	4.3	109.7 est.	Yes	164.5 est.	Yes	RTX 4090D 24GB (China)
Qwen3-Next-80B-A3B-Instruct	81.3	48.6 est.	No	164.0 est.	No	RTX 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

	RTX 4070 Ti Super 16GB	RTX 4090D 24GB (China)
Catalog models that fit	25 of 61	33 of 61
Largest exclusive fit	—	GLM-4.7-Flash (31.2B)

RTX 4070 Ti Super 16GB details → · RTX 4090D 24GB (China) details →