Back to search results
Qwen3.5-0.8B · Q6_K
Qualcomm Snapdragon 7 Gen 4Ollama v0.27L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q6_K) on Qualcomm Snapdragon 7 Gen 4 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
67.49 tok/s
Decode
Decode speed
328.96 tok/s
Prefill
Prefill speed
0.4 s
TTFT
Time to first token
3.78 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 83.77 · Prefill 313.94 ·
- Ollama · IQ2_M Decode 122.21 · Prefill 586.2 ·
- Ollama · Q6_K (current)Decode 67.49 · Prefill 328.96 ·
Core figures
- Decode (avg)
- 67.49 tok/s
- Prefill (avg)
- 328.96 tok/s
- TTFT (avg)
- 0.4 s
- VRAM (avg)
- 3.78 GB
- MTP acceptance rate
- —
- TTFB
- 0.54 GB
- Power draw
- 9.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- Q6_K
- Framework
- Ollama
- Version
- v0.27
- Context length
- 32768 tokens
- Batch size
- 512
- GPU layers
- 99
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Qualcomm Snapdragon 7 Gen 4
- Measured VRAM (avg)
- 3.78 GB
- OS
- Windows 11 23H2
- Driver
- Qualcomm Adreno 7.0
- CUDA
- N/A
- Power draw
- 9.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.27 · Windows 11 23H2 · CUDA N/A · 32768 ctx
67.49 tok/s
Decode
328.96 tok/s
Prefill
0.4 s
TTFT
3.78 GB
VRAM
—
MTP
9.5 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=105 running model_id=51 at Q6_K