Back to search results
Qwen3.8-9B · Q5_K_S
Apple M4 Pro64GBStrata v0.43L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (Q5_K_S) on Apple M4 Pro with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
123.85 tok/s
Decode
Decode speed
643.4 tok/s
Prefill
Prefill speed
1.39 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
5 days ago
Last verified
Performance
- Strata · Q5_K_S (current)Decode 123.85 · Prefill 643.4 ·
Core figures
- Decode (avg)
- 123.85 tok/s
- Prefill (avg)
- 643.4 tok/s
- TTFT (avg)
- 1.39 s
- VRAM (avg)
- 19.11 GB
- MTP acceptance rate
- 0.63
- TTFB
- 0.99 GB
- Power draw
- 73.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- Q5_K_S
- Framework
- Strata
- Version
- v0.43
- Context length
- 16384 tokens
- Batch size
- 1024
- GPU layers
- 15
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M4 Pro
- Nominal VRAM
- 64 GB
- Measured VRAM (avg)
- 19.11 GB
- OS
- macOS 15.0
- Driver
- Apple M4 Pro
- CUDA
- N/A
- Power draw
- 73.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.43 · macOS 15.0 · CUDA N/A · 16384 ctx
123.85 tok/s
Decode
643.4 tok/s
Prefill
1.39 s
TTFT
19.11 GB
VRAM
0.63
MTP
73.8 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=25 running model_id=52 at Q5_K_S