Back to search results
Qwen2.5-0.5B-Instruct · IQ4_XS
Qualcomm Snapdragon X EliteOllama v0.41L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (IQ4_XS) on Qualcomm Snapdragon X Elite with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
131.69 tok/s
Decode
Decode speed
717.01 tok/s
Prefill
Prefill speed
1.58 s
TTFT
Time to first token
2.88 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 (current)Decode 131.69 · Prefill 717.01 ·
- Strata · FP16 Decode 96.34 · Prefill 381.84 ·
Core figures
- Decode (avg)
- 131.69 tok/s
- Prefill (avg)
- 717.01 tok/s
- TTFT (avg)
- 1.58 s
- VRAM (avg)
- 2.88 GB
- MTP acceptance rate
- —
- TTFB
- 1.05 GB
- Power draw
- 9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-0.5B-Instruct
- Quantization
- IQ4_XS
- Framework
- Ollama
- Version
- v0.41
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 99
- 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)
- 2.88 GB
- OS
- Windows 11 23H2
- Driver
- Qualcomm Adreno 7.0
- CUDA
- N/A
- Power draw
- 9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.41 · Windows 11 23H2 · CUDA N/A · 2048 ctx
131.69 tok/s
Decode
717.01 tok/s
Prefill
1.58 s
TTFT
2.88 GB
VRAM
—
MTP
9 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=104 running model_id=59 at IQ4_XS