Grouped by reported model identity. Exact weights, quantizations and software can differ. How results are reviewed
Documented results
12 selected tests| View ReportGeneric LLM | DeepSeek-R1-Distill-Qwen-32B | Relative performance | 4.54 x vs RTX 5080Reported speedup · Per request | — | — | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
|---|---|---|---|---|---|---|
| View ReportGeneric LLM | DeepSeek-R1-Distill-Qwen-32B | Memory | 27.8 GBVRAM usage · Per GPU | — | — | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | DeepSeek-R1-Distill-Qwen-32B | Token speed | 40 output tokens/sToken throughput · Aggregate | — | — | 4 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | DeepSeek-R1-Distill-Qwen-32B | Token speed | 189 output tokens/sToken throughput · Aggregate | — | — | 4 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | DeepSeek-R1-Distill-Qwen-32B | Token speed | 262 output tokens/sToken throughput · Aggregate | — | — | 4 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | DeepSeek-R1-Distill-Qwen-32B | Token speed | 441 output tokens/sToken throughput · Aggregate | — | — | 4 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | DeepSeek-R1-Distill-Qwen-32B | Token speed | 762 output tokens/sToken throughput · Aggregate | — | — | 4 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | DeepSeek-R1-Distill-Qwen-32B | Token speed | 1,272 output tokens/sToken throughput · Aggregate | — | — | 4 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | DeepSeek-R1-Distill-Qwen-32B | Token speed | 1,606 output tokens/sToken throughput · Aggregate | — | — | 4 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | DeepSeek-R1-Distill-Qwen-32B | Token speed | 1,950 output tokens/sToken throughput · Aggregate | — | — | 4 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | DeepSeek-R1-Distill-Qwen-32B | Token speed | 2,214 output tokens/sToken throughput · Aggregate | — | — | 4 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | DeepSeek-R1-Distill-Qwen-32B | Token speed | 2,457 output tokens/sToken throughput · Aggregate | — | — | 4 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPUConfiguration
|
Quantizations and software
Quantizations: Q6
Engines: ComfyUI / PyTorch (footnote wording), LM Studio / llama.cpp, vLLM
This is a selection across sources, not a ranking or a matched experiment. Reading benchmark reports
GPU benchmark pages: R9700