← AI Hashrate 中文

RTX 3090 24GB vs V100 16GB PCIe for Local LLMs

The RTX 3090 24GB has about 4% more memory bandwidth (936 vs 900 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 4% faster on the RTX 3090 24GB. The RTX 3090 24GB fits more of the catalog at Q4/8K — 41 vs 25 of 73 models (24 vs 16 GB VRAM). Largest model that fits the RTX 3090 24GB but not the V100 16GB PCIe: Qwen3.6-35B-A3B (36.0B). MSRP is $1,499 for the RTX 3090 24GB vs $8,000 for the V100 16GB PCIe. MSRP is a launch list price, not live retail — Amazon prices move; click through for the current price. Not retail-shoppable: V100 16GB PCIe (datacenter-class; cloud rental is the realistic way to use it). In the Q4/8K head-to-head below (49 shared models), the RTX 3090 24GB posts the higher tok/s in 37 rows vs 12. Methodology.

Spec comparison

RTX 3090 24GBV100 16GB PCIe
VendorNVIDIANVIDIA
VRAM24 GB16 GB
Memory typeGDDR6XHBM2
Memory bandwidth936 GB/s900 GB/s
TDP350 W250 W
MSRP (list)$1,499$8,000
BuyMSI GeForce RTX 3090 Ventus 3X 24G OC · More listings · eBay · Newegg · B&H Photo

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 49 shared models

ModelParams (B)RTX 3090 24GB tok/sRTX 3090 24GB fitsV100 16GB PCIe tok/sV100 16GB PCIe fitsWinner
MiniCPM5-1B1.08931.4 est.Yes895.6 est.YesRTX 3090 24GB
Qwen3.5-2B2.0503.0 est.Yes483.6 est.YesRTX 3090 24GB
DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx2.3437.4 est.Yes420.5 est.YesRTX 3090 24GB
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF1630.0335.3 est.Yes434.0 est.NoV100 16GB PCIe
Qwen3-30B-A3B-Instruct-250730.5335.3 est.Yes405.4 est.NoV100 16GB PCIe
Qwen3.5-35B-A3B34.7335.3 est.Yes339.8 est.NoV100 16GB PCIe
Qwen3.6-35B-A3B36.0335.3 est.Yes316.9 est.NoRTX 3090 24GB
GLM-4.7-Flash31.2335.3 est.Yes313.0 est.NoRTX 3090 24GB
Ornith-1.0-35B35.0335.3 est.Yes334.2 est.NoRTX 3090 24GB
qwen35b-a3b-fable-sft-abliterated34.7335.3 est.Yes325.2 est.NoRTX 3090 24GB
Llama-3.2-3B-Instruct3.2314.4 est.Yes302.3 est.YesRTX 3090 24GB
gpt-oss-20b21.5161.8 measuredYes268.7 est.YesV100 16GB PCIe
gemma-4-26B-A4B-it25.2264.7 est.Yes254.5 est.YesRTX 3090 24GB
Qwen3-4B-Instruct-25074.0251.5 est.Yes241.8 est.YesRTX 3090 24GB
NVIDIA-Nemotron-3-Nano-4B-BF164.0251.5 est.Yes241.8 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 3090 24GBV100 16GB PCIe
Catalog models that fit41 of 7325 of 73
Largest exclusive fitQwen3.6-35B-A3B (36.0B)

RTX 3090 24GB details → · V100 16GB PCIe details →