← AI Hashrate

A100 80GB SXM4 vs B200 192GB SXM for Local LLMs

The B200 192GB SXM has about 292% more memory bandwidth (8,000 vs 2,039 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 292% faster on the B200 192GB SXM. The B200 192GB SXM fits more of the catalog at Q4/8K — 50 vs 46 of 61 models (192 vs 80 GB VRAM). Largest model that fits the B200 192GB SXM but not the A100 80GB SXM4: Qwen3-235B-A22B (235.1B). MSRP is $15,000 for the A100 80GB SXM4 vs $40,000 for the B200 192GB SXM. MSRP is a launch list price, not live retail — Amazon prices move; click through for the current price. Not retail-shoppable: A100 80GB SXM4, B200 192GB SXM (datacenter-class; cloud rental is the realistic way to use it). In the Q4/8K head-to-head below (54 shared models), the B200 192GB SXM posts the higher tok/s in 54 rows vs 0. Methodology.

Spec comparison

A100 80GB SXM4B200 192GB SXM
VendorNVIDIANVIDIA
VRAM80 GB192 GB
Memory typeHBM2eHBM3e
Memory bandwidth2,039 GB/s8,000 GB/s
TDP400 W1000 W
MSRP (list)$15,000$40,000
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 fitsB200 192GB SXM tok/sB200 192GB SXM fitsWinner
gemma-3-1b-it1.01297.5 est.Yes5000 est.YesB200 192GB SXM
Qwen3-0.6B0.81621.9 est.Yes5000 est.YesB200 192GB SXM
Llama-3.2-1B-Instruct1.21081.3 est.Yes4242.4 est.YesB200 192GB SXM
Qwen3-1.7B2.0648.8 est.Yes2545.5 est.YesB200 192GB SXM
Qwen3-30B-A3B30.5432.5 est.Yes1697.0 est.YesB200 192GB SXM
Qwen3-Coder-30B-A3B-Instruct30.5432.5 est.Yes1697.0 est.YesB200 192GB SXM
GLM-4.7-Flash31.2432.5 est.Yes1697.0 est.YesB200 192GB SXM
Qwen3-30B-A3B-Instruct-250730.5432.5 est.Yes1697.0 est.YesB200 192GB SXM
Qwen3-Next-80B-A3B-Instruct81.3432.5 est.Yes1697.0 est.YesB200 192GB SXM
Qwen3-Coder-Next79.7432.5 est.Yes1697.0 est.YesB200 192GB SXM
Llama-3.2-3B-Instruct3.2405.5 est.Yes1590.9 est.YesB200 192GB SXM
gpt-oss-20b21.5360.4 est.Yes1414.1 est.YesB200 192GB SXM
Phi-4-mini-instruct3.8341.5 est.Yes1339.7 est.YesB200 192GB SXM
Phi-4-mini-reasoning3.8341.5 est.Yes1339.7 est.YesB200 192GB SXM
gemma-3-4b-it4.3332.7 est.Yes1305.4 est.YesB200 192GB SXM

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 SXM4B200 192GB SXM
Catalog models that fit46 of 6150 of 61
Largest exclusive fit—Qwen3-235B-A22B (235.1B)

A100 80GB SXM4 details → · B200 192GB SXM details →