Back to search results
Qwen3-4B-Thinking-2507 · Q8_0
Qualcomm Snapdragon X EliteStrata v0.32L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B-Thinking-2507 (Q8_0) on Qualcomm Snapdragon X Elite with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
48.7 tok/s
Decode
Decode speed
212.72 tok/s
Prefill
Prefill speed
2.46 s
TTFT
Time to first token
11.76 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 81.63 · Prefill 398.71 ·
- Strata · Q8_0 (current)Decode 48.7 · Prefill 212.72 ·
- llama.cpp · Q8_0 Decode 18.5 · Prefill 2.2 ·
Core figures
- Decode (avg)
- 48.7 tok/s
- Prefill (avg)
- 212.72 tok/s
- TTFT (avg)
- 2.46 s
- VRAM (avg)
- 11.76 GB
- MTP acceptance rate
- 0.59
- TTFB
- 0.39 GB
- Power draw
- 9.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B-Thinking-2507
- Quantization
- Q8_0
- Framework
- Strata
- Version
- v0.32
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 8
- 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)
- 11.76 GB
- OS
- Windows 11 23H2
- Driver
- Qualcomm Adreno 7.0
- CUDA
- N/A
- Power draw
- 9.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.32 · Windows 11 23H2 · CUDA N/A · 32768 ctx
48.7 tok/s
Decode
212.72 tok/s
Prefill
2.46 s
TTFT
11.76 GB
VRAM
0.59
MTP
9.6 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=104 running model_id=57 at Q8_0