← AI Hashrate

RTX 3080 10GB vs RTX 3090 24GB for Local LLMs

The RTX 3090 24GB has about 23% more memory bandwidth (936 vs 760 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 23% faster on the RTX 3090 24GB. The RTX 3090 24GB fits more of the catalog at Q4/8K — 33 vs 17 of 61 models (24 vs 10 GB VRAM). Largest model that fits the RTX 3090 24GB but not the RTX 3080 10GB: GLM-4.7-Flash (31.2B). MSRP is $699 for the RTX 3080 10GB vs $1,499 for the RTX 3090 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 (38 shared models), the RTX 3090 24GB posts the higher tok/s in 30 rows vs 8. Methodology.

Spec comparison

RTX 3080 10GBRTX 3090 24GB
VendorNVIDIANVIDIA
VRAM10 GB24 GB
Memory typeGDDR6XGDDR6X
Memory bandwidth760 GB/s936 GB/s
TDP320 W350 W
MSRP (list)$699$1,499
BuySearch Amazon (affiliate)MSI GeForce RTX 3090 Ventus 3X 24G OC (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 38 shared models

ModelParams (B)RTX 3080 10GB tok/sRTX 3080 10GB fitsRTX 3090 24GB tok/sRTX 3090 24GB fitsWinner
Qwen3-0.6B0.8604.5 est.Yes744.5 est.YesRTX 3090 24GB
gemma-3-1b-it1.0483.6 est.Yes595.6 est.YesRTX 3090 24GB
Llama-3.2-1B-Instruct1.2403.0 est.Yes496.4 est.YesRTX 3090 24GB
Qwen3-1.7B2.0241.8 est.Yes297.8 est.YesRTX 3090 24GB
gpt-oss-20b21.5209.1 est.No161.8 measuredYesRTX 3080 10GB
Qwen3-30B-A3B30.5136.3 est.No198.5 est.YesRTX 3090 24GB
Qwen3-Coder-30B-A3B-Instruct30.5136.3 est.No198.5 est.YesRTX 3090 24GB
GLM-4.7-Flash31.2130.9 est.No198.5 est.YesRTX 3090 24GB
Qwen3-30B-A3B-Instruct-250730.5136.3 est.No198.5 est.YesRTX 3090 24GB
Llama-3.2-3B-Instruct3.2151.1 est.Yes186.1 est.YesRTX 3090 24GB
Phi-4-mini-instruct3.8127.3 est.Yes156.7 est.YesRTX 3090 24GB
Phi-4-mini-reasoning3.8127.3 est.Yes156.7 est.YesRTX 3090 24GB
gemma-3-4b-it4.3124.0 est.Yes152.7 est.YesRTX 3090 24GB
Qwen3-4B-Instruct-25074.0120.9 est.Yes148.9 est.YesRTX 3090 24GB
Qwen3-4B-Thinking-25074.0120.9 est.Yes148.9 est.YesRTX 3090 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 3080 10GBRTX 3090 24GB
Catalog models that fit17 of 6133 of 61
Largest exclusive fit—GLM-4.7-Flash (31.2B)

RTX 3080 10GB details → · RTX 3090 24GB details →