Back to search results
Qwen3-1.7B · IQ2_XS
Apple M3 Max36GBvLLM v0.24L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (IQ2_XS) on Apple M3 Max with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
309.15 tok/s
Decode
Decode speed
1,109.54 tok/s
Prefill
Prefill speed
2.17 s
TTFT
Time to first token
3.81 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 309.15 · Prefill 1109.54 ·
- vLLM · Q3_K_L Decode 226.47 · Prefill 1116.37 ·
- Ollama · FP16 Decode 96.85 · Prefill 510.37 ·
- Ollama · IQ4_XS Decode 188.36 · Prefill 704.89 ·
- Strata · Q5_K_S Decode 239.13 · Prefill 849.25 ·
Core figures
- Decode (avg)
- 309.15 tok/s
- Prefill (avg)
- 1,109.54 tok/s
- TTFT (avg)
- 2.17 s
- VRAM (avg)
- 3.81 GB
- MTP acceptance rate
- —
- TTFB
- 2.47 GB
- Power draw
- 37.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- IQ2_XS
- Framework
- vLLM
- Version
- v0.24
- Context length
- 8192 tokens
- Batch size
- 8
- 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 M3 Max
- Nominal VRAM
- 36 GB
- Measured VRAM (avg)
- 3.81 GB
- OS
- macOS 15.0
- Driver
- Apple M3 Max
- CUDA
- N/A
- Power draw
- 37.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.24 · macOS 15.0 · CUDA N/A · 8192 ctx
309.15 tok/s
Decode
1,109.54 tok/s
Prefill
2.17 s
TTFT
3.81 GB
VRAM
—
MTP
37.6 W
Power draw
L2 batch seed 2026-10-10: vLLM on hw_id=4 running model_id=55 at IQ2_XS