Back to search results
Qwen3.8-9B · IQ2_XS
Apple M4 Max128GBvLLM v0.52L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (IQ2_XS) on Apple M4 Max with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
251.74 tok/s
Decode
Decode speed
1,248.2 tok/s
Prefill
Prefill speed
0.56 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
Today
Last verified
Performance
- vLLM · IQ2_XS (current)Decode 251.74 · Prefill 1248.2 ·
- Ollama · Q8_0 Decode 103.18 · Prefill 552.91 ·
- Strata · IQ2_XS Decode 353.9 · Prefill 1746.97 ·
- Strata · IQ3_S Decode 255.89 · Prefill 1167.45 ·
Core figures
- Decode (avg)
- 251.74 tok/s
- Prefill (avg)
- 1,248.2 tok/s
- TTFT (avg)
- 0.56 s
- VRAM (avg)
- 11.17 GB
- MTP acceptance rate
- —
- TTFB
- 2.01 GB
- Power draw
- 63.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- IQ2_XS
- Framework
- vLLM
- Version
- v0.52
- Context length
- 16384 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 M4 Max
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 11.17 GB
- OS
- macOS 15.0
- Driver
- Apple M4 Max
- CUDA
- N/A
- Power draw
- 63.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.52 · macOS 15.0 · CUDA N/A · 16384 ctx
251.74 tok/s
Decode
1,248.2 tok/s
Prefill
0.56 s
TTFT
11.17 GB
VRAM
—
MTP
63.8 W
Power draw
L2 batch seed 2026-10-10: vLLM on hw_id=26 running model_id=52 at IQ2_XS