Back to search results
Qwen3-8B · Q3_K_S
AMD Radeon AI PRO R970032GBllama.cpp v0.51L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q3_K_S) on AMD Radeon AI PRO R9700 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
137.81 tok/s
Decode
Decode speed
521.21 tok/s
Prefill
Prefill speed
0.72 s
TTFT
Time to first token
13.02 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- llama.cpp · IQ2_M Decode 154.04 · Prefill 793.94 ·
- llama.cpp · Q3_K_S (current)Decode 137.81 · Prefill 521.21 ·
- Strata · IQ1_S Decode 246.4 · Prefill 1052.77 ·
- Strata · IQ3_XS Decode 190.7 · Prefill 730.63 ·
Core figures
- Decode (avg)
- 137.81 tok/s
- Prefill (avg)
- 521.21 tok/s
- TTFT (avg)
- 0.72 s
- VRAM (avg)
- 13.02 GB
- MTP acceptance rate
- —
- TTFB
- 1.1 GB
- Power draw
- 283.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q3_K_S
- Framework
- llama.cpp
- Version
- v0.51
- Context length
- 8192 tokens
- Batch size
- 256
- GPU layers
- 20
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- AMD Radeon AI PRO R9700
- Nominal VRAM
- 32 GB
- Measured VRAM (avg)
- 13.02 GB
- OS
- Ubuntu 22.04
- Driver
- amdgpu-pro 24.20
- CUDA
- N/A
- Power draw
- 283.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.51 · Ubuntu 22.04 · CUDA N/A · 8192 ctx
137.81 tok/s
Decode
521.21 tok/s
Prefill
0.72 s
TTFT
13.02 GB
VRAM
—
MTP
283.3 W
Power draw
L2 batch seed 2026-10-13: llama.cpp on hw_id=79 running model_id=53 at Q3_K_S