Back to search results
Qwen3.8-9B · Q3_K_M
Apple M5 Max128GBStrata v0.24L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (Q3_K_M) on Apple M5 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
280.05 tok/s
Decode
Decode speed
1,450.84 tok/s
Prefill
Prefill speed
0.81 s
TTFT
Time to first token
14.95 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 202.52 · Prefill 1021.73 ·
- Strata · Q3_K_M (current)Decode 280.05 · Prefill 1450.84 ·
- Strata · IQ3_XS Decode 320.14 · Prefill 1058.22 ·
- Strata · Q2_K Decode 331.24 · Prefill 1237.62 ·
Core figures
- Decode (avg)
- 280.05 tok/s
- Prefill (avg)
- 1,450.84 tok/s
- TTFT (avg)
- 0.81 s
- VRAM (avg)
- 14.95 GB
- MTP acceptance rate
- 0.77
- TTFB
- 2.24 GB
- Power draw
- 257.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- Q3_K_M
- Framework
- Strata
- Version
- v0.24
- Context length
- 4096 tokens
- Batch size
- 256
- 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
- Apple M5 Max
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 14.95 GB
- OS
- Ubuntu 22.04
- Driver
- 570.86
- CUDA
- 12.8
- Power draw
- 257.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.24 · Ubuntu 22.04 · CUDA 12.8 · 4096 ctx
280.05 tok/s
Decode
1,450.84 tok/s
Prefill
0.81 s
TTFT
14.95 GB
VRAM
0.77
MTP
257.8 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=28 running model_id=52 at Q3_K_M