Back to search results
gemma-4-E4B-it · IQ3_S
NVIDIA Jetson AGX Orin 64GB64GBOllama v0.34L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-E4B-it (IQ3_S) on NVIDIA Jetson AGX Orin 64GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
81.99 tok/s
Decode
Decode speed
290.18 tok/s
Prefill
Prefill speed
2.23 s
TTFT
Time to first token
7.64 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · IQ3_S Decode 89.49 · Prefill 443.95 ·
- vLLM · Q8_0 Decode 46.76 · Prefill 225.72 ·
- Ollama · IQ2_M Decode 83.45 · Prefill 389.24 ·
- Ollama · IQ3_S (current)Decode 81.99 · Prefill 290.18 ·
Core figures
- Decode (avg)
- 81.99 tok/s
- Prefill (avg)
- 290.18 tok/s
- TTFT (avg)
- 2.23 s
- VRAM (avg)
- 7.64 GB
- MTP acceptance rate
- —
- TTFB
- 0.66 GB
- Power draw
- 49.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-E4B-it
- Quantization
- IQ3_S
- Framework
- Ollama
- Version
- v0.34
- Context length
- 4096 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
- NVIDIA Jetson AGX Orin 64GB
- Nominal VRAM
- 64 GB
- Measured VRAM (avg)
- 7.64 GB
- OS
- JetPack 6.0
- Driver
- NVIDIA L4T 36.3
- CUDA
- 12.6
- Power draw
- 49.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.34 · JetPack 6.0 · CUDA 12.6 · 4096 ctx
81.99 tok/s
Decode
290.18 tok/s
Prefill
2.23 s
TTFT
7.64 GB
VRAM
—
MTP
49.2 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=76 running model_id=67 at IQ3_S