Llama-3-8B (checkpoint unspecified) on AMD GPUs
5 results · 3 sources · 5 measurements
Grouped by reported model identity. Exact weights, quantizations and software can differ. How results are reviewed
Documented results
5 selected tests | | | | | | |
|---|
View
Reportllama-bench | Llama-3-8B (checkpoint unspecified)Q4_0Model ref. ↗ | Token speed | — | 2,511.81 tok/sPrefill · mean · per request | — | 1 × RX 9070Single GPU · 16 GB VRAM/GPUConfiguration- Memory
- 16 GB VRAM/GPU
- OS
- Windows 11 Pro 10.0.26200
- Engine
- llama.cpp
- Backend
- Vulkan
- Harness
- RigRoute standard-ai-v0.1 / llama-bench
- Prompt / output
- 512 / 0 tokens
- Context
- Not reported
- Concurrency
- Not reported
- Date
- 2026-09-27
Full record → |
|---|
View
ReportGeneric LLM | Llama-3-8B (checkpoint unspecified)FP8Model ref. ↗ | Token speed | 138 tok/sThroughput · mean · unknown | — | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration- Memory
- 32 GB VRAM/GPU
- OS
- Not reported
- Engine
- vLLM
- Backend
- Not reported
- Harness
- Not reported
- Prompt / output
- ? / ? tokens
- Context
- Not reported
- Concurrency
- Not reported
- Date
- 2025-10-27
Full record → |
|---|
View
ReportGeneric LLM | Llama-3-8B (checkpoint unspecified)FP8Model ref. ↗ | Token speed | 77 tok/sThroughput · unknown | — | — | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration- Memory
- 32 GB VRAM/GPU
- OS
- Not reported
- Engine
- Not reported
- Backend
- Not reported
- Harness
- Author benchmark script (name unreported)
- Prompt / output
- ? / ? tokens
- Context
- Not reported
- Concurrency
- Not reported
- Date
- 2025-10-27
Full record → |
|---|
View
Reportllama-bench | Llama-3-8B (checkpoint unspecified)Q4_0Model ref. ↗ | Token speed | — | — | 102.31 tok/sGeneration · mean · per request | 1 × RX 9070Single GPU · 16 GB VRAM/GPUConfiguration- Memory
- 16 GB VRAM/GPU
- OS
- Windows 11 Pro 10.0.26200
- Engine
- llama.cpp
- Backend
- Vulkan
- Harness
- RigRoute standard-ai-v0.1 / llama-bench
- Prompt / output
- 0 / 128 tokens
- Context
- Not reported
- Concurrency
- Not reported
- Date
- 2026-09-27
Full record → |
|---|
View
ReportGeneric LLM | Llama-3-8B (checkpoint unspecified)Quant not reportedModel ref. ↗ | Token speed | 56 tok/sThroughput · unknown | — | — | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration- Memory
- 32 GB VRAM/GPU
- OS
- Not reported
- Engine
- Not reported
- Backend
- Not reported
- Harness
- Author benchmark script (name unreported)
- Prompt / output
- ? / ? tokens
- Context
- Not reported
- Concurrency
- Not reported
- Date
- 2025-10-27
Full record → |
|---|
Quantizations and software
Quantizations: FP8, Q4_0
Engines: llama.cpp, vLLM
This is a selection across sources, not a ranking or a matched experiment. Reading benchmark reports
GPU benchmark pages: R9700 · RX 9070