Back to search results
Qwen3.8-9B · Q4_K_M
Apple M1Ollama v0.44L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (Q4_K_M) on Apple M1 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
39.07 tok/s
Decode
Decode speed
131.6 tok/s
Prefill
Prefill speed
1.78 s
TTFT
Time to first token
15.2 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- Ollama · IQ3_XS Decode 50.37 · Prefill 163.76 ·
- Ollama · Q4_K_M (current)Decode 39.07 · Prefill 131.6 ·
Core figures
- Decode (avg)
- 39.07 tok/s
- Prefill (avg)
- 131.6 tok/s
- TTFT (avg)
- 1.78 s
- VRAM (avg)
- 15.2 GB
- MTP acceptance rate
- —
- TTFB
- 0.31 GB
- Power draw
- 38.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- Q4_K_M
- Framework
- Ollama
- Version
- v0.44
- Context length
- 4096 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 M1
- Measured VRAM (avg)
- 15.2 GB
- OS
- macOS 15.0
- Driver
- Apple M1
- CUDA
- N/A
- Power draw
- 38.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.44 · macOS 15.0 · CUDA N/A · 4096 ctx
39.07 tok/s
Decode
131.6 tok/s
Prefill
1.78 s
TTFT
15.2 GB
VRAM
—
MTP
38.1 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=99 running model_id=52 at Q4_K_M