Back to search results
Qwen3.5-4B · Q3_K_S
Apple M2 UltravLLM v0.33L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (Q3_K_S) on Apple M2 Ultra with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
169.83 tok/s
Decode
Decode speed
644.07 tok/s
Prefill
Prefill speed
0.8 s
TTFT
Time to first token
7.56 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · Q3_K_L Decode 164.19 · Prefill 535.64 ·
- vLLM · Q3_K_S (current)Decode 169.83 · Prefill 644.07 ·
- Ollama · FP16 Decode 60.62 · Prefill 204.54 ·
- Ollama · IQ2_M Decode 182.13 · Prefill 713.62 ·
Core figures
- Decode (avg)
- 169.83 tok/s
- Prefill (avg)
- 644.07 tok/s
- TTFT (avg)
- 0.8 s
- VRAM (avg)
- 7.56 GB
- MTP acceptance rate
- —
- TTFB
- 1.36 GB
- Power draw
- 63.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- Q3_K_S
- Framework
- vLLM
- Version
- v0.33
- Context length
- 32768 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 M2 Ultra
- Measured VRAM (avg)
- 7.56 GB
- OS
- macOS 15.0
- Driver
- Apple M2 Ultra
- CUDA
- N/A
- Power draw
- 63.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.33 · macOS 15.0 · CUDA N/A · 32768 ctx
169.83 tok/s
Decode
644.07 tok/s
Prefill
0.8 s
TTFT
7.56 GB
VRAM
—
MTP
63.9 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=103 running model_id=48 at Q3_K_S