Back to search results
Qwen3.5-4B · Q6_K
Apple M2 ProOllama v0.49L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (Q6_K) on Apple M2 Pro with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
70.16 tok/s
Decode
Decode speed
240.68 tok/s
Prefill
Prefill speed
2.44 s
TTFT
Time to first token
10.5 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- llama.cpp · IQ2_M Decode 118.95 · Prefill 519.35 ·
- llama.cpp · Q4_K_M Decode 94 · Prefill 499.11 ·
- Ollama · Q6_K (current)Decode 70.16 · Prefill 240.68 ·
Core figures
- Decode (avg)
- 70.16 tok/s
- Prefill (avg)
- 240.68 tok/s
- TTFT (avg)
- 2.44 s
- VRAM (avg)
- 10.5 GB
- MTP acceptance rate
- —
- TTFB
- 0.56 GB
- Power draw
- 18.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- Q6_K
- Framework
- Ollama
- Version
- v0.49
- Context length
- 8192 tokens
- Batch size
- 256
- GPU layers
- 33
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M2 Pro
- Measured VRAM (avg)
- 10.5 GB
- OS
- macOS 15.0
- Driver
- Apple M2 Pro
- CUDA
- N/A
- Power draw
- 18.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.49 · macOS 15.0 · CUDA N/A · 8192 ctx
70.16 tok/s
Decode
240.68 tok/s
Prefill
2.44 s
TTFT
10.5 GB
VRAM
—
MTP
18.1 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=102 running model_id=48 at Q6_K