Back to search results
Qwen3-1.7B · IQ4_XS
Apple M1 ProvLLM v0.25L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (IQ4_XS) on Apple M1 Pro with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
145.02 tok/s
Decode
Decode speed
507.76 tok/s
Prefill
Prefill speed
0.59 s
TTFT
Time to first token
4.75 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · IQ4_XS (current)Decode 145.02 · Prefill 507.76 ·
- Ollama · IQ3_S Decode 144.32 · Prefill 772.26 ·
Core figures
- Decode (avg)
- 145.02 tok/s
- Prefill (avg)
- 507.76 tok/s
- TTFT (avg)
- 0.59 s
- VRAM (avg)
- 4.75 GB
- MTP acceptance rate
- —
- TTFB
- 1.16 GB
- Power draw
- 43.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- IQ4_XS
- Framework
- vLLM
- Version
- v0.25
- Context length
- 2048 tokens
- Batch size
- 8
- GPU layers
- 999
- 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)
- 4.75 GB
- OS
- macOS 15.0
- Driver
- Apple M1 Pro
- CUDA
- N/A
- Power draw
- 43.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.25 · macOS 15.0 · CUDA N/A · 2048 ctx
145.02 tok/s
Decode
507.76 tok/s
Prefill
0.59 s
TTFT
4.75 GB
VRAM
—
MTP
43.8 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=100 running model_id=55 at IQ4_XS