Back to search results
Qwen3.5-9B · IQ2_M
Apple M1 ProvLLM v0.21L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-9B (IQ2_M) on Apple M1 Pro with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
84.15 tok/s
Decode
Decode speed
281.3 tok/s
Prefill
Prefill speed
1.53 s
TTFT
Time to first token
11.93 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- llama.cpp · IQ3_XS Decode 75.72 · Prefill 277.89 ·
- vLLM · IQ2_M (current)Decode 84.15 · Prefill 281.3 ·
- vLLM · Q3_K_S Decode 79.35 · Prefill 395.79 ·
Core figures
- Decode (avg)
- 84.15 tok/s
- Prefill (avg)
- 281.3 tok/s
- TTFT (avg)
- 1.53 s
- VRAM (avg)
- 11.93 GB
- MTP acceptance rate
- —
- TTFB
- 0.67 GB
- Power draw
- 39.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-9B
- Quantization
- IQ2_M
- Framework
- vLLM
- Version
- v0.21
- Context length
- 4096 tokens
- Batch size
- 16
- GPU layers
- 999
- Flash Attention
- Off
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)
- 11.93 GB
- OS
- macOS 15.0
- Driver
- Apple M1 Pro
- CUDA
- N/A
- Power draw
- 39.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.21 · macOS 15.0 · CUDA N/A · 4096 ctx
84.15 tok/s
Decode
281.3 tok/s
Prefill
1.53 s
TTFT
11.93 GB
VRAM
—
MTP
39.1 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=100 running model_id=49 at IQ2_M