Back to search results
Qwen3.8-9B · IQ2_XS
Apple M1 ProOllama v0.51L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (IQ2_XS) on Apple M1 Pro with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
84.92 tok/s
Decode
Decode speed
307.29 tok/s
Prefill
Prefill speed
2.12 s
TTFT
Time to first token
11.17 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · Q2_K Decode 84.42 · Prefill 354.52 ·
- Ollama · IQ2_XS (current)Decode 84.92 · Prefill 307.29 ·
- Ollama · Q3_K_S Decode 67.09 · Prefill 242.11 ·
Core figures
- Decode (avg)
- 84.92 tok/s
- Prefill (avg)
- 307.29 tok/s
- TTFT (avg)
- 2.12 s
- VRAM (avg)
- 11.17 GB
- MTP acceptance rate
- —
- TTFB
- 0.68 GB
- Power draw
- 63.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- IQ2_XS
- Framework
- Ollama
- Version
- v0.51
- Context length
- 16384 tokens
- Batch size
- 512
- GPU layers
- 99
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M1 Pro
- Measured VRAM (avg)
- 11.17 GB
- OS
- macOS 15.0
- Driver
- Apple M1 Pro
- CUDA
- N/A
- Power draw
- 63.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.51 · macOS 15.0 · CUDA N/A · 16384 ctx
84.92 tok/s
Decode
307.29 tok/s
Prefill
2.12 s
TTFT
11.17 GB
VRAM
—
MTP
63.5 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=100 running model_id=52 at IQ2_XS