RTX 4070 Ti Super 16GB vs RTX 4090 24GB for Local LLMs

The RTX 4090 24GB 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 4090 24GB. The RTX 4090 24GB 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 4090 24GB 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 4090 24GB. MSRP is a launch list price, not live retail — Amazon prices move; click through for the current price. In the Q4/8K head-to-head below (44 shared models), the RTX 4090 24GB posts the higher tok/s in 36 rows vs 8. Methodology.

Spec comparison

	RTX 4070 Ti Super 16GB	RTX 4090 24GB
Vendor	NVIDIA	NVIDIA
VRAM	16 GB	24 GB
Memory type	GDDR6X	GDDR6X
Memory bandwidth	672 GB/s	1,008 GB/s
TDP	285 W	450 W
MSRP (list)	$799	$1,599
Buy	Search Amazon (affiliate)	GIGABYTE 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 44 shared models

Model	Params (B)	RTX 4070 Ti Super 16GB tok/s	RTX 4070 Ti Super 16GB fits	RTX 4090 24GB tok/s	RTX 4090 24GB fits	Winner
Qwen3-0.6B	0.8	534.5 est.	Yes	801.8 est.	Yes	RTX 4090 24GB
gemma-3-1b-it	1.0	427.6 est.	Yes	641.5 est.	Yes	RTX 4090 24GB
Llama-3.2-1B-Instruct	1.2	356.4 est.	Yes	534.5 est.	Yes	RTX 4090 24GB
Qwen3-1.7B	2.0	213.8 est.	Yes	320.7 est.	Yes	RTX 4090 24GB
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
gpt-oss-20b	21.5	118.8 est.	Yes	225.2 measured	Yes	RTX 4090 24GB
Llama-3.2-3B-Instruct	3.2	199.0 measured	Yes	200.5 est.	Yes	RTX 4090 24GB
Mistral-7B-Instruct-v0.3	7.2	59.4 est.	Yes	183.3 measured	Yes	RTX 4090 24GB
Qwen3-Coder-Next	79.7	50.5 est.	No	170.4 est.	No	RTX 4090 24GB
Phi-4-mini-instruct	3.8	112.5 est.	Yes	168.8 est.	Yes	RTX 4090 24GB
Phi-4-mini-reasoning	3.8	112.5 est.	Yes	168.8 est.	Yes	RTX 4090 24GB
gemma-3-4b-it	4.3	109.7 est.	Yes	164.5 est.	Yes	RTX 4090 24GB

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 4090 24GB
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 4090 24GB details →