Grouped by reported model identity. Exact weights, quantizations and software can differ. How results are reviewed
Documented results
12 selected tests| View ReportGeneric LLM | Qwen2.5-1.5B-Instruct | Token speed | — | — | 201.56 tok/sGeneration · per request | 1 × W7900Single GPU · 48 GB VRAM/GPUConfiguration
|
|---|---|---|---|---|---|---|
| View Reportllama-bench | Qwen2.5-1.5B-Instruct | Token speed | — | 4,531.77 tok/sPrefill · mean · per request | — | 1 × RX 9060 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen2.5-1.5B-Instruct | Token speed | — | — | 200.76 tok/sGeneration · per request | 1 × W7900Single GPU · 48 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Qwen2.5-1.5B-Instruct | Token speed | — | — | 107.85 tok/sGeneration · mean · per request | 1 × RX 9060 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen2.5-1.5B-Instruct | Token speed | — | — | 202.04 tok/sGeneration · per request | 1 × W7900Single GPU · 48 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Qwen2.5-1.5B-Instruct | Token speed | — | 4,790.91 tok/sPrefill · mean · per request | — | 1 × RX 9060 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen2.5-1.5B-Instruct | Token speed | — | — | 138.81 tok/sGeneration · per request | 1 × W7900Single GPU · 48 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Qwen2.5-1.5B-Instruct | Token speed | — | — | 111.24 tok/sGeneration · mean · per request | 1 × RX 9060 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen2.5-1.5B-Instruct | Token speed | — | — | 140.77 tok/sGeneration · per request | 1 × W7900Single GPU · 48 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen2.5-1.5B-Instruct | Token speed | — | — | 140.91 tok/sGeneration · per request | 1 × W7900Single GPU · 48 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen2.5-1.5B-Instruct | Latency1 concurrent request | 531.32 msModel load time · Whole system | — | — | 1 × W7900Single GPU · 48 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen2.5-1.5B-Instruct | Latency1 concurrent request | 2,748.82 msModel load time · Whole system | — | — | 1 × W7900Single GPU · 48 GB VRAM/GPUConfiguration
|
Quantizations and software
Quantizations: Q4_K_M
Engines: llama.cpp, llama.cpp / llama-cpp-python, VTE
This is a selection across sources, not a ranking or a matched experiment. Reading benchmark reports
GPU benchmark pages: W7900 · RX 9060 XT