Back to search results
Qwen3.8-9B · IQ3_XS
Apple M1Ollama v0.34L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (IQ3_XS) on Apple M1 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
50.37 tok/s
Decode
Decode speed
163.76 tok/s
Prefill
Prefill speed
0.55 s
TTFT
Time to first token
13.82 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 (current)Decode 50.37 · Prefill 163.76 ·
- Ollama · Q4_K_M Decode 39.07 · Prefill 131.6 ·
Core figures
- Decode (avg)
- 50.37 tok/s
- Prefill (avg)
- 163.76 tok/s
- TTFT (avg)
- 0.55 s
- VRAM (avg)
- 13.82 GB
- MTP acceptance rate
- —
- TTFB
- 0.4 GB
- Power draw
- 35.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- IQ3_XS
- Framework
- Ollama
- Version
- v0.34
- 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
- Measured VRAM (avg)
- 13.82 GB
- OS
- macOS 15.0
- Driver
- Apple M1
- CUDA
- N/A
- Power draw
- 35.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.34 · macOS 15.0 · CUDA N/A · 16384 ctx
50.37 tok/s
Decode
163.76 tok/s
Prefill
0.55 s
TTFT
13.82 GB
VRAM
—
MTP
35.9 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=99 running model_id=52 at IQ3_XS