Back to search results
Qwen3-4B-Thinking-2507 · Q8_0
Qualcomm Snapdragon X Elitellama.cpp b1-f027c4fL1 Reproduced
This page aggregates 1 real-world runs of Qwen3-4B-Thinking-2507 (Q8_0) on Qualcomm Snapdragon X Elite with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
18.5 tok/s
Decode
Decode speed
2.2 tok/s
Prefill
Prefill speed
— s
TTFT
Time to first token
— GB
VRAM
VRAM usage
L1 Reproduced
1
Measured runs
1
Independent sources
GitHub
Source platforms
Yesterday
Last verified
Performance
- llama.cpp · Q8_0 (current)Decode 18.5 · Prefill 2.2 ·
Core figures
- Decode (avg)
- 18.5 tok/s
- Prefill (avg)
- 2.2 tok/s
- TTFT (avg)
- — s
- VRAM (avg)
- — GB
- MTP acceptance rate
- —
- TTFB
- — GB
- Power draw
- — W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B-Thinking-2507
- Quantization
- Q8_0
- Framework
- llama.cpp
- Version
- b1-f027c4f
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Qualcomm Snapdragon X Elite
- OS
- Windows
Sources & evidence
1 measured records in total, each traceable to its original source
b1-f027c4f · Windows
18.5 tok/s
Decode
2.2 tok/s
Prefill
— s
TTFT
0 GB
VRAM
—
MTP
— W
Power draw
[ Prompt: 2.2 t/s | Generation: 18.5 t/s ]