Back to search results
Qwen2.5-0.5B-Instruct · FP16
Qualcomm Snapdragon X EliteStrata v0.27L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (FP16) on Qualcomm Snapdragon X Elite with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
96.34 tok/s
Decode
Decode speed
381.84 tok/s
Prefill
Prefill speed
1.75 s
TTFT
Time to first token
4.04 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- Ollama · IQ4_XS Decode 131.69 · Prefill 717.01 ·
- Strata · FP16 (current)Decode 96.34 · Prefill 381.84 ·
Core figures
- Decode (avg)
- 96.34 tok/s
- Prefill (avg)
- 381.84 tok/s
- TTFT (avg)
- 1.75 s
- VRAM (avg)
- 4.04 GB
- MTP acceptance rate
- 0.76
- TTFB
- 0.77 GB
- Power draw
- 10.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-0.5B-Instruct
- Quantization
- FP16
- Framework
- Strata
- Version
- v0.27
- Context length
- 32768 tokens
- Batch size
- 1024
- GPU layers
- 15
- Flash Attention
- Off
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)
- 4.04 GB
- OS
- Windows 11 23H2
- Driver
- Qualcomm Adreno 7.0
- CUDA
- N/A
- Power draw
- 10.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.27 · Windows 11 23H2 · CUDA N/A · 32768 ctx
96.34 tok/s
Decode
381.84 tok/s
Prefill
1.75 s
TTFT
4.04 GB
VRAM
0.76
MTP
10.1 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=104 running model_id=59 at FP16