Grouped by reported model identity. Exact weights, quantizations and software can differ. How results are reviewed
Documented results
6 selected tests| View ReportGeneric LLM | GLM-5.3-Flash-RFA-RFI8-8xR9700 | GPQA Diamond100-task subset; 94 answered, 6 empty32,000 configured context | 85.1 %Accuracy among answered tasks · 80 / 94 | — | — | 8 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
|---|---|---|---|---|---|---|
| View ReportGeneric LLM | GLM-5.3-Flash-RFA-RFI8-8xR9700 | Token speed | — | — | ~34 tok/sGeneration · range lower · per request | 8 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | GLM-5.3-Flash-RFA-RFI8-8xR9700 | Token speed | — | — | ~39 tok/sGeneration · range upper · per request | 8 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | GLM-5.3-Flash-RFA-RFI8-8xR9700 | Token speed | — | — | ~82 tok/sGeneration · range lower · per request | 8 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | GLM-5.3-Flash-RFA-RFI8-8xR9700 | Token speed | — | — | ~88 tok/sGeneration · range upper · per request | 8 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | GLM-5.3-Flash-RFA-RFI8-8xR9700 | Token speed | ~155 tok/sThroughput · aggregate | — | — | 8 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
Quantizations and software
Quantizations: RFA + RFI8 (4.93 bpw)
Engines: vLLM (IronLLM Labs overlay)
This is a selection across sources, not a ranking or a matched experiment. Reading benchmark reports
GPU benchmark pages: R9700