Back to search results
Qwen3.5-0.8B · IQ4_XS
Qualcomm Snapdragon X EliteOllama v0.20L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ4_XS) on Qualcomm Snapdragon X Elite with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
117.58 tok/s
Decode
Decode speed
399 tok/s
Prefill
Prefill speed
2.05 s
TTFT
Time to first token
3.34 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 · Q4_K_M Decode 112.42 · Prefill 515.25 ·
- Ollama · IQ4_XS (current)Decode 117.58 · Prefill 399 ·
- Ollama · Q8_0 Decode 69.82 · Prefill 301.4 ·
Core figures
- Decode (avg)
- 117.58 tok/s
- Prefill (avg)
- 399 tok/s
- TTFT (avg)
- 2.05 s
- VRAM (avg)
- 3.34 GB
- MTP acceptance rate
- —
- TTFB
- 0.94 GB
- Power draw
- 25.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- IQ4_XS
- Framework
- Ollama
- Version
- v0.20
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 28
- 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)
- 3.34 GB
- OS
- Windows 11 23H2
- Driver
- Qualcomm Adreno 7.0
- CUDA
- N/A
- Power draw
- 25.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.20 · Windows 11 23H2 · CUDA N/A · 2048 ctx
117.58 tok/s
Decode
399 tok/s
Prefill
2.05 s
TTFT
3.34 GB
VRAM
—
MTP
25.8 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=104 running model_id=51 at IQ4_XS