Back to search results
Qwen3-8B · Q3_K_S
Qualcomm Snapdragon X ElitevLLM v0.21L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q3_K_S) on Qualcomm Snapdragon X Elite with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
55.63 tok/s
Decode
Decode speed
229.65 tok/s
Prefill
Prefill speed
1.29 s
TTFT
Time to first token
13.02 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · Q2_K Decode 69.03 · Prefill 343.27 ·
- vLLM · Q3_K_S (current)Decode 55.63 · Prefill 229.65 ·
- Strata · IQ2_M Decode 86.12 · Prefill 422.03 ·
- Strata · Q3_K_M Decode 73.79 · Prefill 405.35 ·
Core figures
- Decode (avg)
- 55.63 tok/s
- Prefill (avg)
- 229.65 tok/s
- TTFT (avg)
- 1.29 s
- VRAM (avg)
- 13.02 GB
- MTP acceptance rate
- —
- TTFB
- 0.45 GB
- Power draw
- 34.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q3_K_S
- Framework
- vLLM
- Version
- v0.21
- Context length
- 4096 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
- Qualcomm Snapdragon X Elite
- Measured VRAM (avg)
- 13.02 GB
- OS
- Windows 11 23H2
- Driver
- Qualcomm Adreno 7.0
- CUDA
- N/A
- Power draw
- 34.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.21 · Windows 11 23H2 · CUDA N/A · 4096 ctx
55.63 tok/s
Decode
229.65 tok/s
Prefill
1.29 s
TTFT
13.02 GB
VRAM
—
MTP
34.5 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=104 running model_id=53 at Q3_K_S