Back to search results
Qwen3.5-0.8B · IQ4_XS
Apple M1 ProStrata v0.27L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ4_XS) on Apple M1 Pro with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
263.91 tok/s
Decode
Decode speed
1,056.07 tok/s
Prefill
Prefill speed
1.17 s
TTFT
Time to first token
3.34 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · FP16 Decode 88.25 · Prefill 446.82 ·
- vLLM · IQ3_XS Decode 221.94 · Prefill 834.89 ·
- Strata · IQ4_XS (current)Decode 263.91 · Prefill 1056.07 ·
- Strata · Q6_K Decode 165.63 · Prefill 531.23 ·
Core figures
- Decode (avg)
- 263.91 tok/s
- Prefill (avg)
- 1,056.07 tok/s
- TTFT (avg)
- 1.17 s
- VRAM (avg)
- 3.34 GB
- MTP acceptance rate
- 0.5
- TTFB
- 2.11 GB
- Power draw
- 35.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- IQ4_XS
- Framework
- Strata
- Version
- v0.27
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 12
- Flash Attention
- Off
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)
- 3.34 GB
- OS
- macOS 15.0
- Driver
- Apple M1 Pro
- CUDA
- N/A
- Power draw
- 35.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.27 · macOS 15.0 · CUDA N/A · 2048 ctx
263.91 tok/s
Decode
1,056.07 tok/s
Prefill
1.17 s
TTFT
3.34 GB
VRAM
0.5
MTP
35.3 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=100 running model_id=51 at IQ4_XS