Back to search results
gemma-4-E2B-it · Q4_K_M
Intel Arc 140Vllama.cpp v0.47L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-E2B-it (Q4_K_M) on Intel Arc 140V with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
78.89 tok/s
Decode
Decode speed
345.96 tok/s
Prefill
Prefill speed
0.74 s
TTFT
Time to first token
5.54 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 (current)Decode 78.89 · Prefill 345.96 ·
- llama.cpp · Q8_0 Decode 53.13 · Prefill 172.01 ·
- vLLM · Q4_K_M Decode 93.69 · Prefill 438.33 ·
Core figures
- Decode (avg)
- 78.89 tok/s
- Prefill (avg)
- 345.96 tok/s
- TTFT (avg)
- 0.74 s
- VRAM (avg)
- 5.54 GB
- MTP acceptance rate
- —
- TTFB
- 0.63 GB
- Power draw
- 216.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-E2B-it
- Quantization
- Q4_K_M
- Framework
- llama.cpp
- Version
- v0.47
- Context length
- 8192 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
- Intel Arc 140V
- Measured VRAM (avg)
- 5.54 GB
- OS
- Ubuntu 24.04
- Driver
- Intel Arc 31.0.101.5186
- CUDA
- 12.6
- Power draw
- 216.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.47 · Ubuntu 24.04 · CUDA 12.6 · 8192 ctx
78.89 tok/s
Decode
345.96 tok/s
Prefill
0.74 s
TTFT
5.54 GB
VRAM
—
MTP
216.3 W
Power draw
L2 batch seed 2026-10-16: llama.cpp on hw_id=98 running model_id=66 at Q4_K_M