Back to search results
Qwen3-8B · Q5_K_S
AMD Strix Point (Radeon 890M)Strata v0.39L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q5_K_S) on AMD Strix Point (Radeon 890M) with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
66.77 tok/s
Decode
Decode speed
312.73 tok/s
Prefill
Prefill speed
1.31 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
2 days ago
Last verified
Performance
- vLLM · Q4_K_M Decode 56.8 · Prefill 217.7 ·
- Strata · IQ1_S Decode 121.73 · Prefill 484.23 ·
- Strata · Q5_K_S (current)Decode 66.77 · Prefill 312.73 ·
Core figures
- Decode (avg)
- 66.77 tok/s
- Prefill (avg)
- 312.73 tok/s
- TTFT (avg)
- 1.31 s
- VRAM (avg)
- 15.2 GB
- MTP acceptance rate
- 0.56
- TTFB
- 0.53 GB
- Power draw
- 76.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q5_K_S
- Framework
- Strata
- Version
- v0.39
- Context length
- 32768 tokens
- Batch size
- 1024
- GPU layers
- 12
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- AMD Strix Point (Radeon 890M)
- Measured VRAM (avg)
- 15.2 GB
- OS
- Windows 11 23H2
- Driver
- 555.85
- CUDA
- N/A
- Power draw
- 76.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.39 · Windows 11 23H2 · CUDA N/A · 32768 ctx
66.77 tok/s
Decode
312.73 tok/s
Prefill
1.31 s
TTFT
15.2 GB
VRAM
0.56
MTP
76.7 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=89 running model_id=53 at Q5_K_S