Back to search results
Qwen3-8B · Q8_0
Apple M4 Pro64GBOllama v0.42L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q8_0) on Apple M4 Pro with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
61.9 tok/s
Decode
Decode speed
265.27 tok/s
Prefill
Prefill speed
0.87 s
TTFT
Time to first token
21.42 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 Decode 131.41 · Prefill 579.15 ·
- Ollama · Q8_0 (current)Decode 61.9 · Prefill 265.27 ·
Core figures
- Decode (avg)
- 61.9 tok/s
- Prefill (avg)
- 265.27 tok/s
- TTFT (avg)
- 0.87 s
- VRAM (avg)
- 21.42 GB
- MTP acceptance rate
- —
- TTFB
- 0.5 GB
- Power draw
- 117.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q8_0
- Framework
- Ollama
- Version
- v0.42
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 33
- 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)
- 21.42 GB
- OS
- macOS 15.0
- Driver
- Apple M4 Pro
- CUDA
- N/A
- Power draw
- 117.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.42 · macOS 15.0 · CUDA N/A · 32768 ctx
61.9 tok/s
Decode
265.27 tok/s
Prefill
0.87 s
TTFT
21.42 GB
VRAM
—
MTP
117.6 W
Power draw
L2 batch seed 2026-10-13: Ollama on hw_id=25 running model_id=53 at Q8_0