RTX 3090 Ti 24GB vs Titan X Pascal 12GB for Local LLMs

The RTX 3090 Ti 24GB has about 110% more memory bandwidth (1,008 vs 480 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 110% faster on the RTX 3090 Ti 24GB. The RTX 3090 Ti 24GB fits more of the catalog at Q4/8K — 35 vs 18 of 69 models (24 vs 12 GB VRAM). Largest model that fits the RTX 3090 Ti 24GB but not the Titan X Pascal 12GB: Qwen3.6-35B-A3B (36.0B). MSRP is $1,999 for the RTX 3090 Ti 24GB vs $1,200 for the Titan X Pascal 12GB. 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 (41 shared models), the RTX 3090 Ti 24GB posts the higher tok/s in 37 rows vs 4. Methodology.

Spec comparison

	RTX 3090 Ti 24GB	Titan X Pascal 12GB
Vendor	NVIDIA	NVIDIA
VRAM	24 GB	12 GB
Memory type	GDDR6X	GDDR5X
Memory bandwidth	1,008 GB/s	480 GB/s
TDP	450 W	250 W
MSRP (list)	$1,999	$1,200
Buy	Search Amazon (affiliate)	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 41 shared models

Model	Params (B)	RTX 3090 Ti 24GB tok/s	RTX 3090 Ti 24GB fits	Titan X Pascal 12GB tok/s	Titan X Pascal 12GB fits	Winner
MiniCPM5-1B	1.08	593.9 est.	Yes	282.8 est.	Yes	RTX 3090 Ti 24GB
Qwen3.5-2B	2.0	320.7 est.	Yes	152.7 est.	Yes	RTX 3090 Ti 24GB
DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx	2.3	278.9 est.	Yes	132.8 est.	Yes	RTX 3090 Ti 24GB
Qwen3.6-35B-A3B	36.0	213.8 est.	Yes	95.7 est.	No	RTX 3090 Ti 24GB
Qwen3.5-35B-A3B	34.7	213.8 est.	Yes	102.6 est.	No	RTX 3090 Ti 24GB
GLM-4.7-Flash	31.2	213.8 est.	Yes	118.5 est.	No	RTX 3090 Ti 24GB
Qwen3-30B-A3B-Instruct-2507	30.5	213.8 est.	Yes	123.5 est.	No	RTX 3090 Ti 24GB
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16	30.0	213.8 est.	Yes	135.8 est.	No	RTX 3090 Ti 24GB
Ornith-1.0-35B	35.0	213.8 est.	Yes	96.0 est.	No	RTX 3090 Ti 24GB
qwen35b-a3b-fable-sft-abliterated	34.7	213.8 est.	Yes	97.5 est.	No	RTX 3090 Ti 24GB
Llama-3.2-3B-Instruct	3.2	200.5 est.	Yes	95.5 est.	Yes	RTX 3090 Ti 24GB
gpt-oss-20b	21.5	178.2 est.	Yes	189.3 est.	No	Titan X Pascal 12GB
Qwen3-Coder-Next	79.7	174.1 est.	No	20.7 est.	No	RTX 3090 Ti 24GB
gemma-4-26B-A4B-it	25.2	168.8 est.	Yes	135.0 est.	No	RTX 3090 Ti 24GB
Qwen3-Next-80B-A3B-Instruct	81.3	167.5 est.	No	19.9 est.	No	RTX 3090 Ti 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 3090 Ti 24GB	Titan X Pascal 12GB
Catalog models that fit	35 of 69	18 of 69
Largest exclusive fit	Qwen3.6-35B-A3B (36.0B)	—

RTX 3090 Ti 24GB details → · Titan X Pascal 12GB details →