Back to search results
Qwen3.5-4B · FP16
Qualcomm Snapdragon X ElitevLLM v0.45L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (FP16) on Qualcomm Snapdragon X Elite with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
32.76 tok/s
Decode
Decode speed
107.43 tok/s
Prefill
Prefill speed
1.72 s
TTFT
Time to first token
15.2 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 83.91 · Prefill 412.44 ·
- vLLM · FP16 (current)Decode 32.76 · Prefill 107.43 ·
Core figures
- Decode (avg)
- 32.76 tok/s
- Prefill (avg)
- 107.43 tok/s
- TTFT (avg)
- 1.72 s
- VRAM (avg)
- 15.2 GB
- MTP acceptance rate
- —
- TTFB
- 0.26 GB
- Power draw
- 13.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- FP16
- Framework
- vLLM
- Version
- v0.45
- 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
- Qualcomm Snapdragon X Elite
- Measured VRAM (avg)
- 15.2 GB
- OS
- Windows 11 23H2
- Driver
- Qualcomm Adreno 7.0
- CUDA
- N/A
- Power draw
- 13.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.45 · Windows 11 23H2 · CUDA N/A · 8192 ctx
32.76 tok/s
Decode
107.43 tok/s
Prefill
1.72 s
TTFT
15.2 GB
VRAM
—
MTP
13.5 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=104 running model_id=48 at FP16