4 × RX 7900 XTX LLM benchmarks
4 results · 4 measurements · 2 sources
Device specifications
| Variant | Memory | Memory type | Bus | Bandwidth | FP16 matrix | INT8 matrix |
|---|---|---|---|---|---|---|
| RX 7900 XTX ↗ | 24 GB | GDDR6 | 384-bit | 960 GB/s | 123 TFLOPS | 123 TOPS |
Manufacturer specifications. Shared system RAM is not dedicated VRAM. Unreported values remain —; measured LLM results retain their reported configuration.
Selected reported tests
4 of 4 resultsSource-reported results, selected across reports by documentation quality. Match configurations before comparing values.
| View Reportllama-bench | Llama-2-7B | Token speed | — | 1,545.39 tok/sPrefill · mean · per request | — | 4 × RX 7900 XTXMulti-GPU · split unknown · 24 GB VRAM/GPUConfiguration
|
|---|---|---|---|---|---|---|
| View Reportllama-bench | Llama-2-7B | Token speed | — | 1,484.04 tok/sPrefill · mean · per request | — | 4 × RX 7900 XTXMulti-GPU · split unknown · 24 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Llama-2-7B | Token speed | — | — | 88.12 tok/sGeneration · mean · per request | 4 × RX 7900 XTXMulti-GPU · split unknown · 24 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Llama-2-7B | Token speed | — | — | 91.48 tok/sGeneration · mean · per request | 4 × RX 7900 XTXMulti-GPU · split unknown · 24 GB VRAM/GPUConfiguration
|
Models and software in this collection
Model families: Llama 2
Engines: llama.cpp
Methodology and evidence standards · Download the research dataset