GeekRadar / The comparison desk
COMPARE.
Tested systems8 × AMD Instinct MI300X 192GB HBM3
Tested system
- Processor
- AMD EPYC 9534
- Graphics
- AMD Instinct MI300X 192GB HBM3
- Accelerator count
- 8
- Nodes
- 1
Recorded results
Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.
MLPerf Inference / gpt-oss-120bOffline · v6.1 · Tokens/s
8 × AMD Instinct MI300X 192GB HBM3
30,198.40* Tokens/s
- Accuracy target / result
- exact_match: 83.713
- Weight precision
- fp8
- Division
- closed
- System type
- datacenter
- Availability
- available
- Cores per processor
- 64
- Processors per node
- 2
- Nodes
- 1
- Total accelerators
- 8
- Software stack
- vLLM 0.24.0 (stock vllm/vllm-openai-rocm:v0.24.0), ROCm 7.2.1
- Operating system
- Ubuntu 22.04.5 LTS
MLPerf Inference / gpt-oss-120bServer · v6.1 · Tokens/s
8 × AMD Instinct MI300X 192GB HBM3
24,863* Tokens/s
- Accuracy target / result
- exact_match: 82.842
- Weight precision
- fp8
- Division
- closed
- System type
- datacenter
- Availability
- available
- Cores per processor
- 64
- Processors per node
- 2
- Nodes
- 1
- Total accelerators
- 8
- Software stack
- vLLM 0.24.0 (stock vllm/vllm-openai-rocm:v0.24.0), ROCm 7.2.1
- Operating system
- Ubuntu 22.04.5 LTS
Processing & platform
- Processor
- AMD EPYC 9534
- Graphics
- AMD Instinct MI300X 192GB HBM3
Connectivity & software
- Operating system
- Ubuntu 22.04.5 LTS
System configuration
- Reported host core count
- 64
- Processors per node
- 2
- Accelerator count
- 8
- Nodes
- 1
- Software stack
- vLLM 0.24.0 (stock vllm/vllm-openai-rocm:v0.24.0), ROCm 7.2.1
- Submission division
- closed
0 selected Compare 0
* Provisional data