elephant-1 · Q2_K
This page aggregates 1 real-world runs of elephant-1 (Q2_K) on NVIDIA RTX 3060 12GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
70.07 tok/s
Decode
Decode speed
259.24 tok/s
Prefill
Prefill speed
0.62 s
TTFT
Time to first token
11.4 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
13 days ago
Last verified
Performance
- vLLM · Q2_K (current)Decode 70.07 · Prefill 259.24 ·
Core figures
- Decode (avg)
- 70.07 tok/s
- Prefill (avg)
- 259.24 tok/s
- TTFT (avg)
- 0.62 s
- VRAM (avg)
- 11.4 GB
- MTP acceptance rate
- —
- TTFB
- 0.56 GB
- Power draw
- 147.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- elephant-1
- Quantization
- Q2_K
- Framework
- vLLM
- Version
- v0.42
- Context length
- 2048 tokens
- Batch size
- 16
- 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
- NVIDIA RTX 3060 12GB
- Nominal VRAM
- 12 GB
- Measured VRAM (avg)
- 11.4 GB
- OS
- Ubuntu 24.04
- Driver
- 565.57
- CUDA
- 12.6
- Power draw
- 147.9 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
v0.42 · Ubuntu 24.04 · CUDA 12.6 · 2048 ctx
70.07 tok/s
Decode
259.24 tok/s
Prefill
0.62 s
TTFT
11.4 GB
VRAM
—
MTP
147.9 W
Power draw
L2 batch seed 2026-10-22: vLLM on hw_id=15 running model_id=95 at Q2_K