Back to search results
Qwen3.8-9B · Q4_K_M
AMD Strix Point (Radeon 890M)Strata v0.50L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (Q4_K_M) on AMD Strix Point (Radeon 890M) with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
68.09 tok/s
Decode
Decode speed
270.12 tok/s
Prefill
Prefill speed
2.14 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 · Q2_K Decode 74.53 · Prefill 292.59 ·
- vLLM · Q3_K_M Decode 62.84 · Prefill 312.12 ·
- Strata · Q4_K_M (current)Decode 68.09 · Prefill 270.12 ·
Core figures
- Decode (avg)
- 68.09 tok/s
- Prefill (avg)
- 270.12 tok/s
- TTFT (avg)
- 2.14 s
- VRAM (avg)
- 15.2 GB
- MTP acceptance rate
- 0.76
- TTFB
- 0.54 GB
- Power draw
- 58.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- Q4_K_M
- Framework
- Strata
- Version
- v0.50
- Context length
- 32768 tokens
- Batch size
- 512
- 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
- 560.94
- CUDA
- N/A
- Power draw
- 58.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.50 · Windows 11 23H2 · CUDA N/A · 32768 ctx
68.09 tok/s
Decode
270.12 tok/s
Prefill
2.14 s
TTFT
15.2 GB
VRAM
0.76
MTP
58.5 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=89 running model_id=52 at Q4_K_M