Back to search results
Qwen3-1.7B · Q4_K_M
Apple M5 Pro64GBvLLM v0.46L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (Q4_K_M) on Apple M5 Pro with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
233.37 tok/s
Decode
Decode speed
1,190.9 tok/s
Prefill
Prefill speed
2 s
TTFT
Time to first token
5.03 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- llama.cpp · IQ2_M Decode 311.55 · Prefill 1641.2 ·
- llama.cpp · Q5_K_S Decode 197.87 · Prefill 839.49 ·
- vLLM · Q4_K_M (current)Decode 233.37 · Prefill 1190.9 ·
- vLLM · Q5_K_S Decode 229.77 · Prefill 936.19 ·
Core figures
- Decode (avg)
- 233.37 tok/s
- Prefill (avg)
- 1,190.9 tok/s
- TTFT (avg)
- 2 s
- VRAM (avg)
- 5.03 GB
- MTP acceptance rate
- —
- TTFB
- 1.87 GB
- Power draw
- 64.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q4_K_M
- Framework
- vLLM
- Version
- v0.46
- Context length
- 32768 tokens
- Batch size
- 32
- 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 M5 Pro
- Nominal VRAM
- 64 GB
- Measured VRAM (avg)
- 5.03 GB
- OS
- macOS 15.0
- Driver
- Apple M5 Pro
- CUDA
- N/A
- Power draw
- 64.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.46 · macOS 15.0 · CUDA N/A · 32768 ctx
233.37 tok/s
Decode
1,190.9 tok/s
Prefill
2 s
TTFT
5.03 GB
VRAM
—
MTP
64.7 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=27 running model_id=55 at Q4_K_M