Back to search results
Qwen3.8-9B · Q5_K_S
AMD Strix Halo (Radeon 8060S)Strata v0.45L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (Q5_K_S) on AMD Strix Halo (Radeon 8060S) with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
95.58 tok/s
Decode
Decode speed
525.15 tok/s
Prefill
Prefill speed
1.95 s
TTFT
Time to first token
19.11 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · Q3_K_L Decode 88.34 · Prefill 283.42 ·
- vLLM · Q8_0 Decode 54.8 · Prefill 273.05 ·
- Strata · IQ3_XS Decode 138.39 · Prefill 445.74 ·
- Strata · Q5_K_S (current)Decode 95.58 · Prefill 525.15 ·
Core figures
- Decode (avg)
- 95.58 tok/s
- Prefill (avg)
- 525.15 tok/s
- TTFT (avg)
- 1.95 s
- VRAM (avg)
- 19.11 GB
- MTP acceptance rate
- 0.75
- TTFB
- 0.76 GB
- Power draw
- 105.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- Q5_K_S
- Framework
- Strata
- Version
- v0.45
- Context length
- 32768 tokens
- Batch size
- 1024
- GPU layers
- 8
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- AMD Strix Halo (Radeon 8060S)
- Measured VRAM (avg)
- 19.11 GB
- OS
- macOS 15.0
- Driver
- 555.85
- CUDA
- N/A
- Power draw
- 105.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.45 · macOS 15.0 · CUDA N/A · 32768 ctx
95.58 tok/s
Decode
525.15 tok/s
Prefill
1.95 s
TTFT
19.11 GB
VRAM
0.75
MTP
105.9 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=87 running model_id=52 at Q5_K_S