Instinct MI100 x4 vs RTX 3080
Best verified output tok/s per model (single-stream generation). Hover a value for the quant.
Instinct MI100 x41 verified run · best 132.4 tok/s
RTX 30809 verified runs · best 277.8 tok/s
| Model | Instinct MI100 x4 | RTX 3080 |
|---|
| LFM2.5-8B-A1B | — | 277.8 Q6_K |
| Qwen3.8-27B | 132.4 INT8 | 44.4 IQ2_XXS |
| Ornith-1.5-9B | — | 82.8 Q6_K |
| Qwen3.8-27B-Uncensored | — | 74.1 IQ2_XXS |
| Bonsai-27B | — | 72.9 Q1_0 |
| gemma-4-12B-it-qat | — | 71.2 Q4_0 |
| Ornith-1.5-35B-A3B | — | 64.4 Q4_K_M |
| gpt-oss-20b | — | 57.1 MXFP4 |
| Muse-Glimmer-30B | — | 6.0 Q4_K_M |
Head-to-head (models tested on both): Instinct MI100 x4 1 · RTX 3080 0 · tied 0 · data as of Sep 23, 2026. Full rules: methodology.
Related reading: RTX 5090 vs 3090 · quantization · Value index · Full board