Back to search results
gemma-4-E2B-it · Q3_K_M
Qualcomm Snapdragon 7 Gen 4vLLM v0.21L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-E2B-it (Q3_K_M) on Qualcomm Snapdragon 7 Gen 4 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
80.58 tok/s
Decode
Decode speed
389.4 tok/s
Prefill
Prefill speed
0.97 s
TTFT
Time to first token
4.96 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_M (current)Decode 80.58 · Prefill 389.4 ·
- vLLM · Q8_0 Decode 46.45 · Prefill 213.34 ·
- Ollama · Q4_K_S Decode 62.77 · Prefill 308.77 ·
Core figures
- Decode (avg)
- 80.58 tok/s
- Prefill (avg)
- 389.4 tok/s
- TTFT (avg)
- 0.97 s
- VRAM (avg)
- 4.96 GB
- MTP acceptance rate
- —
- TTFB
- 0.64 GB
- Power draw
- 17 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-E2B-it
- Quantization
- Q3_K_M
- Framework
- vLLM
- Version
- v0.21
- Context length
- 16384 tokens
- Batch size
- 32
- GPU layers
- 999
- 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)
- 4.96 GB
- OS
- Windows 11 23H2
- Driver
- Qualcomm Adreno 7.0
- CUDA
- N/A
- Power draw
- 17 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.21 · Windows 11 23H2 · CUDA N/A · 16384 ctx
80.58 tok/s
Decode
389.4 tok/s
Prefill
0.97 s
TTFT
4.96 GB
VRAM
—
MTP
17 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=105 running model_id=66 at Q3_K_M