llama3.2:1b on A100, H100 — 2026-04-18
2026-04-18T06:24:24.000Z → 2026-04-18T06:24:37.239Z
On 2026-04-18, llama3.2:1b ran across A100, H100. H100 finished first at 589.7 tok/s, 12× faster than A100. The per-million-token cost: $1.17 (H100) vs $4.50 (A100) — the surprise: the headline GPU H100 was also the cheapest per-million tokens, coming in 3.8× less than A100.
Podium
H100
1st
thunder-h100
- peak tok/s
- 589.7
- avg tok/s
- 589.7
- $ / 1M tok
- $1.17
A100
2nd
thunder-a100
- peak tok/s
- 48.2
- avg tok/s
- 48.2
- $ / 1M tok
- $4.50