llama3.2:1b on A6000, A100, H100 — 2026-04-17
2026-04-17T21:53:43.000Z → 2026-04-17T21:54:19.177Z
On 2026-04-17, llama3.2:1b ran across A6000, A100, H100. H100 finished first at 590.0 tok/s, 22× faster than A6000. The per-million-token cost: $1.17 (H100) vs $3.60 (A6000) — the surprise: the headline GPU H100 was also the cheapest per-million tokens, coming in 3.1× less than A6000.
Podium
H100
1st
thunder-h100
- peak tok/s
- 590.0
- avg tok/s
- 590.0
- $ / 1M tok
- $1.17
A100
2nd
thunder-a100
- peak tok/s
- 44.2
- avg tok/s
- 44.2
- $ / 1M tok
- $4.90
A6000
3rd
thunder-a6000
- peak tok/s
- 27.0
- avg tok/s
- 27.0
- $ / 1M tok
- $3.60