Back to search results
Llama-3-8B-Instruct · Q5_K_S
AMD Radeon RX 907016GBllama.cpp v0.54L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3-8B-Instruct (Q5_K_S) on AMD Radeon RX 9070 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
113.29 tok/s
Decode
Decode speed
563 tok/s
Prefill
Prefill speed
1.42 s
TTFT
Time to first token
15.2 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · Q5_K_S (current)Decode 113.29 · Prefill 563 ·
Core figures
- Decode (avg)
- 113.29 tok/s
- Prefill (avg)
- 563 tok/s
- TTFT (avg)
- 1.42 s
- VRAM (avg)
- 15.2 GB
- MTP acceptance rate
- —
- TTFB
- 0.91 GB
- Power draw
- 215.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3-8B-Instruct
- Quantization
- Q5_K_S
- Framework
- llama.cpp
- Version
- v0.54
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 33
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- AMD Radeon RX 9070
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 15.2 GB
- OS
- Windows 11 23H2
- Driver
- amdgpu 6.11
- CUDA
- 12.4
- Power draw
- 215.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.54 · Windows 11 23H2 · CUDA 12.4 · 2048 ctx
113.29 tok/s
Decode
563 tok/s
Prefill
1.42 s
TTFT
15.2 GB
VRAM
—
MTP
215.4 W
Power draw
L2 batch seed 2026-10-18: llama.cpp on hw_id=21 running model_id=69 at Q5_K_S