Back to search results
Qwen3.5-4B · Q4_K_S
Apple M1Strata v0.45L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (Q4_K_S) on Apple M1 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
87.2 tok/s
Decode
Decode speed
469.35 tok/s
Prefill
Prefill speed
0.46 s
TTFT
Time to first token
8.65 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- llama.cpp · IQ2_M Decode 88.05 · Prefill 311.52 ·
- llama.cpp · Q4_K_M Decode 55.57 · Prefill 194.52 ·
- Strata · Q4_K_S (current)Decode 87.2 · Prefill 469.35 ·
Core figures
- Decode (avg)
- 87.2 tok/s
- Prefill (avg)
- 469.35 tok/s
- TTFT (avg)
- 0.46 s
- VRAM (avg)
- 8.65 GB
- MTP acceptance rate
- 0.58
- TTFB
- 0.7 GB
- Power draw
- 21.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- Q4_K_S
- Framework
- Strata
- Version
- v0.45
- Context length
- 2048 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 M1
- Measured VRAM (avg)
- 8.65 GB
- OS
- macOS 15.0
- Driver
- Apple M1
- CUDA
- N/A
- Power draw
- 21.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.45 · macOS 15.0 · CUDA N/A · 2048 ctx
87.2 tok/s
Decode
469.35 tok/s
Prefill
0.46 s
TTFT
8.65 GB
VRAM
0.58
MTP
21.8 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=99 running model_id=48 at Q4_K_S