Back to search results
Qwen3-4B · IQ4_XS
Qualcomm Snapdragon X ElitevLLM v0.22L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B (IQ4_XS) on Qualcomm Snapdragon X Elite with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
66.12 tok/s
Decode
Decode speed
360.69 tok/s
Prefill
Prefill speed
1.39 s
TTFT
Time to first token
8.32 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · IQ4_XS (current)Decode 66.12 · Prefill 360.69 ·
- vLLM · Q3_K_M Decode 74.16 · Prefill 385.13 ·
- Strata · FP16 Decode 39.4 · Prefill 159.35 ·
Core figures
- Decode (avg)
- 66.12 tok/s
- Prefill (avg)
- 360.69 tok/s
- TTFT (avg)
- 1.39 s
- VRAM (avg)
- 8.32 GB
- MTP acceptance rate
- —
- TTFB
- 0.53 GB
- Power draw
- 30.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B
- Quantization
- IQ4_XS
- Framework
- vLLM
- Version
- v0.22
- Context length
- 2048 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
- Qualcomm Snapdragon X Elite
- Measured VRAM (avg)
- 8.32 GB
- OS
- Windows 11 23H2
- Driver
- Qualcomm Adreno 7.0
- CUDA
- N/A
- Power draw
- 30.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.22 · Windows 11 23H2 · CUDA N/A · 2048 ctx
66.12 tok/s
Decode
360.69 tok/s
Prefill
1.39 s
TTFT
8.32 GB
VRAM
—
MTP
30.8 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=104 running model_id=54 at IQ4_XS