Back to search results
Qwen3.8-9B · IQ1_S
Apple M2 UltravLLM v0.36L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (IQ1_S) on Apple M2 Ultra with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
152.06 tok/s
Decode
Decode speed
546.19 tok/s
Prefill
Prefill speed
2.21 s
TTFT
Time to first token
10.04 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · IQ1_S (current)Decode 152.06 · Prefill 546.19 ·
- Strata · Q4_K_M Decode 129.12 · Prefill 454.27 ·
- Strata · Q8_0 Decode 89.33 · Prefill 303.19 ·
Core figures
- Decode (avg)
- 152.06 tok/s
- Prefill (avg)
- 546.19 tok/s
- TTFT (avg)
- 2.21 s
- VRAM (avg)
- 10.04 GB
- MTP acceptance rate
- —
- TTFB
- 1.22 GB
- Power draw
- 23.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- IQ1_S
- Framework
- vLLM
- Version
- v0.36
- Context length
- 4096 tokens
- Batch size
- 16
- GPU layers
- 999
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M2 Ultra
- Measured VRAM (avg)
- 10.04 GB
- OS
- macOS 15.0
- Driver
- Apple M2 Ultra
- CUDA
- N/A
- Power draw
- 23.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.36 · macOS 15.0 · CUDA N/A · 4096 ctx
152.06 tok/s
Decode
546.19 tok/s
Prefill
2.21 s
TTFT
10.04 GB
VRAM
—
MTP
23.9 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=103 running model_id=52 at IQ1_S