elephant-1 · Q4_K_S
This page aggregates 1 real-world runs of elephant-1 (Q4_K_S) on NVIDIA RTX 3090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
69.84 tok/s
Decode
Decode speed
337.36 tok/s
Prefill
Prefill speed
0.56 s
TTFT
Time to first token
16.84 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
13 days ago
Last verified
Performance
- Ollama · Q4_K_S (current)Decode 69.84 · Prefill 337.36 ·
- Strata · IQ1_S Decode 163.87 · Prefill 748 ·
Core figures
- Decode (avg)
- 69.84 tok/s
- Prefill (avg)
- 337.36 tok/s
- TTFT (avg)
- 0.56 s
- VRAM (avg)
- 16.84 GB
- MTP acceptance rate
- —
- TTFB
- 0.56 GB
- Power draw
- 251.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- elephant-1
- Quantization
- Q4_K_S
- Framework
- Ollama
- Version
- v0.44
- Context length
- 4096 tokens
- Batch size
- 512
- 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
- NVIDIA RTX 3090
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 16.84 GB
- OS
- Windows 11 23H2
- Driver
- 565.57
- CUDA
- 12.6
- Power draw
- 251.1 W
Get started
Original model resources
Base model resources may not match this quantization. Use the verified deployment weights above when available.
Sources & evidence
1 measured records in total, each traceable to its original source
v0.44 · Windows 11 23H2 · CUDA 12.6 · 4096 ctx
69.84 tok/s
Decode
337.36 tok/s
Prefill
0.56 s
TTFT
16.84 GB
VRAM
—
MTP
251.1 W
Power draw
L2 batch seed 2026-10-22: Ollama on hw_id=2 running model_id=95 at Q4_K_S