← AI Hashrate 中文

RTX 3080 10GB vs Titan X Pascal 12GB for Local LLMs

The RTX 3080 10GB has about 58% more memory bandwidth (760 vs 480 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 58% faster on the RTX 3080 10GB. The Titan X Pascal 12GB fits more of the catalog at Q4/8K — 18 vs 17 of 69 models (12 vs 10 GB VRAM). Largest model that fits the Titan X Pascal 12GB but not the RTX 3080 10GB: OLMo-2-1124-13B-Instruct (13.7B). MSRP is $699 for the RTX 3080 10GB 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 (39 shared models), the RTX 3080 10GB posts the higher tok/s in 39 rows vs 0. Methodology.

Spec comparison

RTX 3080 10GBTitan X Pascal 12GB
VendorNVIDIANVIDIA
VRAM10 GB12 GB
Memory typeGDDR6XGDDR5X
Memory bandwidth760 GB/s480 GB/s
TDP320 W250 W
MSRP (list)$699$1,200
BuySearch 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 39 shared models

ModelParams (B)RTX 3080 10GB tok/sRTX 3080 10GB fitsTitan X Pascal 12GB tok/sTitan X Pascal 12GB fitsWinner
MiniCPM5-1B1.08447.8 est.Yes282.8 est.YesRTX 3080 10GB
Qwen3.5-2B2.0241.8 est.Yes152.7 est.YesRTX 3080 10GB
DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx2.3210.3 est.Yes132.8 est.YesRTX 3080 10GB
gpt-oss-20b21.5208.0 est.No189.3 est.NoRTX 3080 10GB
Llama-3.2-3B-Instruct3.2151.1 est.Yes95.5 est.YesRTX 3080 10GB
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF1630.0149.1 est.No135.8 est.NoRTX 3080 10GB
gemma-4-26B-A4B-it25.2148.3 est.No135.0 est.NoRTX 3080 10GB
Qwen3-30B-A3B-Instruct-250730.5135.7 est.No123.5 est.NoRTX 3080 10GB
GLM-4.7-Flash31.2130.2 est.No118.5 est.NoRTX 3080 10GB
Qwen3-4B-Instruct-25074.0120.9 est.Yes76.4 est.YesRTX 3080 10GB
NVIDIA-Nemotron-3-Nano-4B-BF164.0120.9 est.Yes76.4 est.YesRTX 3080 10GB
Qwen3-4B-Thinking-25074.0120.9 est.Yes76.4 est.YesRTX 3080 10GB
Qwen3.5-35B-A3B34.7112.8 est.No102.6 est.NoRTX 3080 10GB
qwen35b-a3b-fable-sft-abliterated34.7107.1 est.No97.5 est.NoRTX 3080 10GB
Ornith-1.0-35B35.0105.4 est.No96.0 est.NoRTX 3080 10GB

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 3080 10GBTitan X Pascal 12GB
Catalog models that fit17 of 6918 of 69
Largest exclusive fitOLMo-2-1124-13B-Instruct (13.7B)

RTX 3080 10GB details → · Titan X Pascal 12GB details →