Back to search results
Qwen3.5-4B · IQ3_S
Apple M1 ProStrata v0.40L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (IQ3_S) on Apple M1 Pro with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
156.63 tok/s
Decode
Decode speed
693.97 tok/s
Prefill
Prefill speed
0.91 s
TTFT
Time to first token
7.64 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 104.97 · Prefill 349.69 ·
- Strata · IQ3_S (current)Decode 156.63 · Prefill 693.97 ·
Core figures
- Decode (avg)
- 156.63 tok/s
- Prefill (avg)
- 693.97 tok/s
- TTFT (avg)
- 0.91 s
- VRAM (avg)
- 7.64 GB
- MTP acceptance rate
- 0.46
- TTFB
- 1.25 GB
- Power draw
- 65.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- IQ3_S
- Framework
- Strata
- Version
- v0.40
- Context length
- 16384 tokens
- Batch size
- 1024
- 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 Pro
- Measured VRAM (avg)
- 7.64 GB
- OS
- macOS 15.0
- Driver
- Apple M1 Pro
- CUDA
- N/A
- Power draw
- 65.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.40 · macOS 15.0 · CUDA N/A · 16384 ctx
156.63 tok/s
Decode
693.97 tok/s
Prefill
0.91 s
TTFT
7.64 GB
VRAM
0.46
MTP
65.1 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=100 running model_id=48 at IQ3_S