Back to search results
Qwen3-8B · Q3_K_M
Apple M4 Pro64GBvLLM v0.33L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q3_K_M) on Apple M4 Pro with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
131.41 tok/s
Decode
Decode speed
579.15 tok/s
Prefill
Prefill speed
2.01 s
TTFT
Time to first token
13.52 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- vLLM · Q3_K_M (current)Decode 131.41 · Prefill 579.15 ·
- Ollama · Q8_0 Decode 61.9 · Prefill 265.27 ·
Core figures
- Decode (avg)
- 131.41 tok/s
- Prefill (avg)
- 579.15 tok/s
- TTFT (avg)
- 2.01 s
- VRAM (avg)
- 13.52 GB
- MTP acceptance rate
- —
- TTFB
- 1.05 GB
- Power draw
- 37.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q3_K_M
- Framework
- vLLM
- Version
- v0.33
- Context length
- 16384 tokens
- Batch size
- 16
- 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 M4 Pro
- Nominal VRAM
- 64 GB
- Measured VRAM (avg)
- 13.52 GB
- OS
- macOS 15.0
- Driver
- Apple M4 Pro
- CUDA
- N/A
- Power draw
- 37.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.33 · macOS 15.0 · CUDA N/A · 16384 ctx
131.41 tok/s
Decode
579.15 tok/s
Prefill
2.01 s
TTFT
13.52 GB
VRAM
—
MTP
37.5 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=25 running model_id=53 at Q3_K_M