Back to search results
Qwen3-1.7B · IQ4_XS
Apple M2 UltravLLM v0.31L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (IQ4_XS) on Apple M2 Ultra with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
221.65 tok/s
Decode
Decode speed
888.85 tok/s
Prefill
Prefill speed
0.49 s
TTFT
Time to first token
4.75 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 · Q2_K Decode 247.88 · Prefill 1258.27 ·
- llama.cpp · Q4_K_M Decode 200.31 · Prefill 817.12 ·
- vLLM · IQ4_XS (current)Decode 221.65 · Prefill 888.85 ·
- vLLM · Q6_K Decode 162.21 · Prefill 522.8 ·
Core figures
- Decode (avg)
- 221.65 tok/s
- Prefill (avg)
- 888.85 tok/s
- TTFT (avg)
- 0.49 s
- VRAM (avg)
- 4.75 GB
- MTP acceptance rate
- —
- TTFB
- 1.77 GB
- Power draw
- 36.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- IQ4_XS
- Framework
- vLLM
- Version
- v0.31
- Context length
- 2048 tokens
- Batch size
- 8
- 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 M2 Ultra
- Measured VRAM (avg)
- 4.75 GB
- OS
- macOS 15.0
- Driver
- Apple M2 Ultra
- CUDA
- N/A
- Power draw
- 36.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.31 · macOS 15.0 · CUDA N/A · 2048 ctx
221.65 tok/s
Decode
888.85 tok/s
Prefill
0.49 s
TTFT
4.75 GB
VRAM
—
MTP
36.2 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=103 running model_id=55 at IQ4_XS