# R9: FX100 on Huawei Ascend 910B: Inference and Training Benchmark (vs. NFS Baseline)

> Three comparison groups against an NFS baseline on an Ascend platform with 8 × Huawei Atlas 910B: model loading for inference (DeepSeek-32B / 70B), training weight and checkpoint I/O (Qwen-7B), and training-data acceleration (YOLOv8 / COCO). The platform is Ascend 910B, not MI308X, and is labeled as such wherever this site quotes it.

URL: https://vuke.top/en/evidence/R9 · Updated November 12, 2026

Three comparison groups against an NFS baseline on an Ascend platform with 8 × Huawei Atlas 910B: model loading for inference (DeepSeek-32B / 70B), training weight and checkpoint I/O (Qwen-7B), and training-data acceleration (YOLOv8 / COCO). The platform is Ascend 910B, not MI308X, and is labeled as such wherever this site quotes it.

- Report: R9
- Date: 2026-05-30
- Type: Benchmark report
- Test platform: 8 × Huawei Atlas 910B (Kunpeng-920)

## Key findings

- DeepSeek-32B serving load: 691 s → 112 s (6.2×)
- DeepSeek-70B serving load: 1399 s → 150 s (9.3×)
- Also covers training weight / checkpoint I/O and training-data acceleration

## Figures this report supports

| Metric | Value | Baseline | Detail | Source |
| --- | --- | --- | --- | --- |
| Faster model loading | 6.2–9.3× | vs. NFS, on Huawei Ascend 910B | On Huawei Atlas 910B: DeepSeek-32B serving load 691 s → 112 s (6.2×); DeepSeek-70B 1399 s → 150 s (9.3×). | Measured · [R9](https://vuke.top/en/evidence/R9) |

## Request the original reports

Tell us which report IDs you need and what for, and we will reply with how to get them. The R8 code export and raw data are provided on request in the same way.

- Company: Xinyuanyi (Tianjin) Semiconductor Equipment Co., Ltd.
- Contact: Wang Limin
- Phone: +86 131 6181 8898
- Email: mingxin@agentmail.to (The inbox is monitored and triaged by AI around the clock)