Back to search results
Qwen3.8-9B · Q3_K_L
Qualcomm Snapdragon X Elitellama.cpp v0.54L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (Q3_K_L) on Qualcomm Snapdragon X Elite with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
50.63 tok/s
Decode
Decode speed
217.32 tok/s
Prefill
Prefill speed
0.58 s
TTFT
Time to first token
15.2 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 · Q3_K_L (current)Decode 50.63 · Prefill 217.32 ·
- vLLM · Q3_K_L Decode 51.08 · Prefill 205.33 ·
Core figures
- Decode (avg)
- 50.63 tok/s
- Prefill (avg)
- 217.32 tok/s
- TTFT (avg)
- 0.58 s
- VRAM (avg)
- 15.2 GB
- MTP acceptance rate
- —
- TTFB
- 0.41 GB
- Power draw
- 32.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- Q3_K_L
- Framework
- llama.cpp
- Version
- v0.54
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 33
- 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)
- 15.2 GB
- OS
- Windows 11 23H2
- Driver
- Qualcomm Adreno 7.0
- CUDA
- N/A
- Power draw
- 32.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.54 · Windows 11 23H2 · CUDA N/A · 32768 ctx
50.63 tok/s
Decode
217.32 tok/s
Prefill
0.58 s
TTFT
15.2 GB
VRAM
—
MTP
32.5 W
Power draw
L2 batch seed 2026-10-16: llama.cpp on hw_id=104 running model_id=52 at Q3_K_L