← AI Hashrate

A100 80GB SXM4 vs H200 141GB SXM5 for Local LLMs

The H200 141GB SXM5 has about 135% more memory bandwidth (4,800 vs 2,039 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 135% faster on the H200 141GB SXM5. The H200 141GB SXM5 fits more of the catalog at Q4/8K — 48 vs 46 of 61 models (141 vs 80 GB VRAM). Largest model that fits the H200 141GB SXM5 but not the A100 80GB SXM4: MiniMax-M2.7 (228.7B). MSRP is $15,000 for the A100 80GB SXM4 vs $35,000 for the H200 141GB SXM5. MSRP is a launch list price, not live retail — Amazon prices move; click through for the current price. Not retail-shoppable: A100 80GB SXM4, H200 141GB SXM5 (datacenter-class; cloud rental is the realistic way to use it). In the Q4/8K head-to-head below (54 shared models), the H200 141GB SXM5 posts the higher tok/s in 54 rows vs 0. Methodology.

Spec comparison

A100 80GB SXM4H200 141GB SXM5
VendorNVIDIANVIDIA
VRAM80 GB141 GB
Memory typeHBM2eHBM3e
Memory bandwidth2,039 GB/s4,800 GB/s
TDP400 W700 W
MSRP (list)$15,000$35,000
Buy——

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 54 shared models

ModelParams (B)A100 80GB SXM4 tok/sA100 80GB SXM4 fitsH200 141GB SXM5 tok/sH200 141GB SXM5 fitsWinner
Qwen3-0.6B0.81621.9 est.Yes3818.2 est.YesH200 141GB SXM5
gemma-3-1b-it1.01297.5 est.Yes3054.5 est.YesH200 141GB SXM5
Llama-3.2-1B-Instruct1.21081.3 est.Yes2545.5 est.YesH200 141GB SXM5
Qwen3-1.7B2.0648.8 est.Yes1527.3 est.YesH200 141GB SXM5
Qwen3-30B-A3B30.5432.5 est.Yes1018.2 est.YesH200 141GB SXM5
Qwen3-Coder-30B-A3B-Instruct30.5432.5 est.Yes1018.2 est.YesH200 141GB SXM5
GLM-4.7-Flash31.2432.5 est.Yes1018.2 est.YesH200 141GB SXM5
Qwen3-30B-A3B-Instruct-250730.5432.5 est.Yes1018.2 est.YesH200 141GB SXM5
Qwen3-Next-80B-A3B-Instruct81.3432.5 est.Yes1018.2 est.YesH200 141GB SXM5
Qwen3-Coder-Next79.7432.5 est.Yes1018.2 est.YesH200 141GB SXM5
Llama-3.2-3B-Instruct3.2405.5 est.Yes954.5 est.YesH200 141GB SXM5
gpt-oss-20b21.5360.4 est.Yes848.5 est.YesH200 141GB SXM5
Phi-4-mini-instruct3.8341.5 est.Yes803.8 est.YesH200 141GB SXM5
Phi-4-mini-reasoning3.8341.5 est.Yes803.8 est.YesH200 141GB SXM5
gemma-3-4b-it4.3332.7 est.Yes783.2 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

A100 80GB SXM4H200 141GB SXM5
Catalog models that fit46 of 6148 of 61
Largest exclusive fit—MiniMax-M2.7 (228.7B)

A100 80GB SXM4 details → · H200 141GB SXM5 details →