Back to search results
gemma-4-E4B-it · Q3_K_M
Intel Arc A770 16GB16GBllama.cpp v0.37L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-E4B-it (Q3_K_M) on Intel Arc A770 16GB with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
76.26 tok/s
Decode
Decode speed
388.45 tok/s
Prefill
Prefill speed
2.29 s
TTFT
Time to first token
7.81 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 · Q3_K_M (current)Decode 76.26 · Prefill 388.45 ·
- llama.cpp · Q4_K_S Decode 63.45 · Prefill 318.27 ·
- Strata · Q3_K_L Decode 103.12 · Prefill 533.63 ·
- Strata · Q4_K_S Decode 90.28 · Prefill 352.31 ·
Core figures
- Decode (avg)
- 76.26 tok/s
- Prefill (avg)
- 388.45 tok/s
- TTFT (avg)
- 2.29 s
- VRAM (avg)
- 7.81 GB
- MTP acceptance rate
- —
- TTFB
- 0.61 GB
- Power draw
- 221.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-E4B-it
- Quantization
- Q3_K_M
- Framework
- llama.cpp
- Version
- v0.37
- Context length
- 16384 tokens
- Batch size
- 256
- GPU layers
- 33
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Intel Arc A770 16GB
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 7.81 GB
- OS
- Windows 11 23H2
- Driver
- Intel Arc 31.0.101.5186
- CUDA
- 12.6
- Power draw
- 221.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.37 · Windows 11 23H2 · CUDA 12.6 · 16384 ctx
76.26 tok/s
Decode
388.45 tok/s
Prefill
2.29 s
TTFT
7.81 GB
VRAM
—
MTP
221.9 W
Power draw
L2 batch seed 2026-10-16: llama.cpp on hw_id=97 running model_id=67 at Q3_K_M