Grouped by reported model identity. Exact weights, quantizations and software can differ. How results are reviewed
Documented results
7 selected tests| View Reportllama-bench | Qwen3-0.6B | Token speed | — | 18,116 tok/sPrefill · per request | — | 1 × RX 9070 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
|---|---|---|---|---|---|---|
| View ReportGeneric LLM | Qwen3-0.6B | LatencyNative Windows offline latency / tiny8 input · 1 output | 77.49 msLatency · Per request 77.75 msLatency · Per request | — | — | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Qwen3-0.6B | Token speed | — | — | 571.9 tok/sGeneration · per request | 1 × RX 9070 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3-0.6B | LatencyNative Windows offline latency / tiny8 input · 1 output | 61.82 msLatency · Per request 61.82 msLatency · Per request | — | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Qwen3-0.6B | Token speed | — | 10,831 tok/sPrefill · per request | — | 1 × RX 9070 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3-0.6B | LatencyNative Windows offline latency / tiny8 input · 1 output | 59.04 msLatency · Per request 59 msLatency · Per request | — | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Qwen3-0.6B | Token speed | — | — | 292.2 tok/sGeneration · per request | 1 × RX 9070 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
Quantizations and software
Quantizations: Q4_K_M
Engines: llama.cpp, vLLM_for_AMD
This is a selection across sources, not a ranking or a matched experiment. Reading benchmark reports
GPU benchmark pages: R9700 · RX 9070 XT