Back to search results
Qwen3.5-4B · FP16
Apple M2 UltraOllama v0.47L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (FP16) on Apple M2 Ultra with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
60.62 tok/s
Decode
Decode speed
204.54 tok/s
Prefill
Prefill speed
0.12 s
TTFT
Time to first token
17.64 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 Decode 169.83 · Prefill 644.07 ·
- Ollama · FP16 (current)Decode 60.62 · Prefill 204.54 ·
- Ollama · IQ2_M Decode 182.13 · Prefill 713.62 ·
Core figures
- Decode (avg)
- 60.62 tok/s
- Prefill (avg)
- 204.54 tok/s
- TTFT (avg)
- 0.12 s
- VRAM (avg)
- 17.64 GB
- MTP acceptance rate
- —
- TTFB
- 0.48 GB
- Power draw
- 29.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- FP16
- Framework
- Ollama
- Version
- v0.47
- Context length
- 32768 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 M2 Ultra
- Measured VRAM (avg)
- 17.64 GB
- OS
- macOS 15.0
- Driver
- Apple M2 Ultra
- CUDA
- N/A
- Power draw
- 29.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.47 · macOS 15.0 · CUDA N/A · 32768 ctx
60.62 tok/s
Decode
204.54 tok/s
Prefill
0.12 s
TTFT
17.64 GB
VRAM
—
MTP
29.6 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=103 running model_id=48 at FP16