Crusoe Cloud 64x8 MI355X (8x AMD Instinct MI355X 288GB HBM3e): edge AI benchmarks
Key results
| Workload | Best result | Model · precision | Power · perf/W | Grade · date | Source |
|---|---|---|---|---|---|
| LLM serving (MLPerf datacenter) | 5749440 tok/s batch unknown | MLPerf gpt-oss-120b mxfp4 · vLLM 0.22.1 (ROCm 7.2.2), PyTorch 2.10 | unknown | A 2026-09-16 (published) | MLPerf Inference v6.1, closed division, data-centre suite |
Best published result per workload, across model sizes. For like-for-like groups, open the per-workload tables below.
Show data — per-workload tables
object detection
No published object detection results for Crusoe Cloud 64x8 MI355X (8x AMD Instinct MI355X 288GB HBM3e) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
instance segmentation
No published instance segmentation results for Crusoe Cloud 64x8 MI355X (8x AMD Instinct MI355X 288GB HBM3e) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
pose estimation
No published pose estimation results for Crusoe Cloud 64x8 MI355X (8x AMD Instinct MI355X 288GB HBM3e) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
image classification
No published image classification results for Crusoe Cloud 64x8 MI355X (8x AMD Instinct MI355X 288GB HBM3e) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
semantic segmentation
No published semantic segmentation results for Crusoe Cloud 64x8 MI355X (8x AMD Instinct MI355X 288GB HBM3e) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
speech-to-text
No published speech-to-text results for Crusoe Cloud 64x8 MI355X (8x AMD Instinct MI355X 288GB HBM3e) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
LLM generation
No published LLM generation results for Crusoe Cloud 64x8 MI355X (8x AMD Instinct MI355X 288GB HBM3e) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
LLM serving (MLPerf datacenter)
| Like-for-like group | Best result | Model · precision · stack | Grade | Power | Source · date | Rank in group |
|---|---|---|---|---|---|---|
| LLM >40B · b=unknown | 5749440 tok/s | MLPerf gpt-oss-120b mxfp4 · vLLM 0.22.1 (ROCm 7.2.2), PyTorch 2.10 | A | unknown power n/a | MLPerf Inference v6.1, closed division, data-centre suite 2026-09-16 (published) | 1 of 93 |
| unknown · b=unknown | 2901950 tok/s | MLPerf deepseek-r1 fp4 · SGLang 0.5.15.post1 (ROCm 7.2.0), PyTorch 2.x | A | unknown power n/a | MLPerf Inference v6.1, closed division, data-centre suite 2026-09-16 (published) | 1 of 32 |
How to read these numbers
Machine-readable: /find.json (see llms.txt); full tables are in “Show data”. Confidence grades: A audited MLPerf closed · B documented third-party · C community · D vendor-published · E estimate. Unknown values are shown as unknown, never estimated. Generated 2026-10-16 from public sources.