Back to search results
gemma-4-E4B-it · Q8_0
Qualcomm Snapdragon X EliteOllama v0.53L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-E4B-it (Q8_0) on Qualcomm Snapdragon X Elite with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
35.6 tok/s
Decode
Decode speed
173.17 tok/s
Prefill
Prefill speed
2.25 s
TTFT
Time to first token
11.76 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · Q3_K_L Decode 70.71 · Prefill 337.65 ·
- vLLM · Q4_K_M Decode 62.62 · Prefill 304.49 ·
- Ollama · Q3_K_L Decode 58.9 · Prefill 275.23 ·
- Ollama · Q8_0 (current)Decode 35.6 · Prefill 173.17 ·
Core figures
- Decode (avg)
- 35.6 tok/s
- Prefill (avg)
- 173.17 tok/s
- TTFT (avg)
- 2.25 s
- VRAM (avg)
- 11.76 GB
- MTP acceptance rate
- —
- TTFB
- 0.28 GB
- Power draw
- 19.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-E4B-it
- Quantization
- Q8_0
- Framework
- Ollama
- Version
- v0.53
- Context length
- 32768 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)
- 11.76 GB
- OS
- Windows 11 23H2
- Driver
- Qualcomm Adreno 7.0
- CUDA
- N/A
- Power draw
- 19.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.53 · Windows 11 23H2 · CUDA N/A · 32768 ctx
35.6 tok/s
Decode
173.17 tok/s
Prefill
2.25 s
TTFT
11.76 GB
VRAM
—
MTP
19.6 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=104 running model_id=67 at Q8_0