← AI Hashrate

H200 141GB SXM5 vs RTX 3060 12GB for Local LLMs

The H200 141GB SXM5 has about 1233% more memory bandwidth (4,800 vs 360 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 1233% faster on the H200 141GB SXM5. The H200 141GB SXM5 fits more of the catalog at Q4/8K — 48 vs 18 of 61 models (141 vs 12 GB VRAM). Largest model that fits the H200 141GB SXM5 but not the RTX 3060 12GB: MiniMax-M2.7 (228.7B). MSRP is $35,000 for the H200 141GB SXM5 vs $329 for the RTX 3060 12GB. MSRP is a launch list price, not live retail — Amazon prices move; click through for the current price. Not retail-shoppable: H200 141GB SXM5 (datacenter-class; cloud rental is the realistic way to use it). In the Q4/8K head-to-head below (40 shared models), the H200 141GB SXM5 posts the higher tok/s in 40 rows vs 0. Methodology.

Spec comparison

H200 141GB SXM5RTX 3060 12GB
VendorNVIDIANVIDIA
VRAM141 GB12 GB
Memory typeHBM3eGDDR6
Memory bandwidth4,800 GB/s360 GB/s
TDP700 W170 W
MSRP (list)$35,000$329
Buy—MSI GeForce RTX 3060 Ventus 2X 12G 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 40 shared models

ModelParams (B)H200 141GB SXM5 tok/sH200 141GB SXM5 fitsRTX 3060 12GB tok/sRTX 3060 12GB fitsWinner
Qwen3-0.6B0.83818.2 est.Yes286.4 est.YesH200 141GB SXM5
gemma-3-1b-it1.03054.5 est.Yes229.1 est.YesH200 141GB SXM5
Llama-3.2-1B-Instruct1.22545.5 est.Yes190.9 est.YesH200 141GB SXM5
Qwen3-1.7B2.01527.3 est.Yes114.5 est.YesH200 141GB SXM5
Qwen3-30B-A3B30.51018.2 est.Yes93.0 est.NoH200 141GB SXM5
Qwen3-Coder-30B-A3B-Instruct30.51018.2 est.Yes93.0 est.NoH200 141GB SXM5
GLM-4.7-Flash31.21018.2 est.Yes89.3 est.NoH200 141GB SXM5
Qwen3-30B-A3B-Instruct-250730.51018.2 est.Yes93.0 est.NoH200 141GB SXM5
Qwen3-Next-80B-A3B-Instruct81.31018.2 est.Yes14.6 est.NoH200 141GB SXM5
Qwen3-Coder-Next79.71018.2 est.Yes15.2 est.NoH200 141GB SXM5
Llama-3.2-3B-Instruct3.2954.5 est.Yes122.9 measuredYesH200 141GB SXM5
gpt-oss-20b21.5848.5 est.Yes84.0 measuredNoH200 141GB SXM5
Phi-4-mini-instruct3.8803.8 est.Yes60.3 est.YesH200 141GB SXM5
Phi-4-mini-reasoning3.8803.8 est.Yes60.3 est.YesH200 141GB SXM5
gemma-3-4b-it4.3783.2 est.Yes58.7 est.YesH200 141GB SXM5

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

H200 141GB SXM5RTX 3060 12GB
Catalog models that fit48 of 6118 of 61
Largest exclusive fitMiniMax-M2.7 (228.7B)—

H200 141GB SXM5 details → · RTX 3060 12GB details →