Back to search results
Qwen3-1.7B · Q3_K_M
Qualcomm Snapdragon X EliteOllama v0.51L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (Q3_K_M) on Qualcomm Snapdragon X Elite with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
88.26 tok/s
Decode
Decode speed
401.25 tok/s
Prefill
Prefill speed
2.07 s
TTFT
Time to first token
4.53 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · IQ4_XS Decode 100.93 · Prefill 494.53 ·
- Ollama · Q3_K_M (current)Decode 88.26 · Prefill 401.25 ·
Core figures
- Decode (avg)
- 88.26 tok/s
- Prefill (avg)
- 401.25 tok/s
- TTFT (avg)
- 2.07 s
- VRAM (avg)
- 4.53 GB
- MTP acceptance rate
- —
- TTFB
- 0.71 GB
- Power draw
- 28.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q3_K_M
- Framework
- Ollama
- Version
- v0.51
- Context length
- 32768 tokens
- Batch size
- 512
- GPU layers
- 20
- 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)
- 4.53 GB
- OS
- Windows 11 23H2
- Driver
- Qualcomm Adreno 7.0
- CUDA
- N/A
- Power draw
- 28.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.51 · Windows 11 23H2 · CUDA N/A · 32768 ctx
88.26 tok/s
Decode
401.25 tok/s
Prefill
2.07 s
TTFT
4.53 GB
VRAM
—
MTP
28.8 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=104 running model_id=55 at Q3_K_M