Back to search results
Qwen3-4B-Thinking-2507 · IQ1_S
Apple M1 ProStrata v0.38L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B-Thinking-2507 (IQ1_S) on Apple M1 Pro with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
163.46 tok/s
Decode
Decode speed
649.89 tok/s
Prefill
Prefill speed
0.4 s
TTFT
Time to first token
5.63 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · IQ3_S Decode 94.49 · Prefill 403.53 ·
- Strata · IQ1_S (current)Decode 163.46 · Prefill 649.89 ·
- Strata · Q2_K Decode 151.41 · Prefill 638.55 ·
Core figures
- Decode (avg)
- 163.46 tok/s
- Prefill (avg)
- 649.89 tok/s
- TTFT (avg)
- 0.4 s
- VRAM (avg)
- 5.63 GB
- MTP acceptance rate
- 0.57
- TTFB
- 1.31 GB
- Power draw
- 50.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B-Thinking-2507
- Quantization
- IQ1_S
- Framework
- Strata
- Version
- v0.38
- Context length
- 8192 tokens
- Batch size
- 256
- GPU layers
- 5
- 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)
- 5.63 GB
- OS
- macOS 15.0
- Driver
- Apple M1 Pro
- CUDA
- N/A
- Power draw
- 50.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.38 · macOS 15.0 · CUDA N/A · 8192 ctx
163.46 tok/s
Decode
649.89 tok/s
Prefill
0.4 s
TTFT
5.63 GB
VRAM
0.57
MTP
50.4 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=100 running model_id=57 at IQ1_S