Back to search results
Qwen3.5-4B · Q4_K_S
Apple M4 Pro64GBOllama v0.43L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (Q4_K_S) on Apple M4 Pro with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
136.48 tok/s
Decode
Decode speed
705.2 tok/s
Prefill
Prefill speed
1.75 s
TTFT
Time to first token
8.65 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- Ollama · Q4_K_S (current)Decode 136.48 · Prefill 705.2 ·
Core figures
- Decode (avg)
- 136.48 tok/s
- Prefill (avg)
- 705.2 tok/s
- TTFT (avg)
- 1.75 s
- VRAM (avg)
- 8.65 GB
- MTP acceptance rate
- —
- TTFB
- 1.09 GB
- Power draw
- 128.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- Q4_K_S
- Framework
- Ollama
- Version
- v0.43
- Context length
- 4096 tokens
- Batch size
- 256
- GPU layers
- 20
- 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)
- 8.65 GB
- OS
- macOS 15.0
- Driver
- Apple M4 Pro
- CUDA
- N/A
- Power draw
- 128.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.43 · macOS 15.0 · CUDA N/A · 4096 ctx
136.48 tok/s
Decode
705.2 tok/s
Prefill
1.75 s
TTFT
8.65 GB
VRAM
—
MTP
128.8 W
Power draw
L2 batch seed 2026-10-13: Ollama on hw_id=25 running model_id=48 at Q4_K_S