elephant-1 · IQ1_S
This page aggregates 1 real-world runs of elephant-1 (IQ1_S) on NVIDIA RTX PRO 6000 Blackwell 96GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
275.81 tok/s
Decode
Decode speed
1,195.7 tok/s
Prefill
Prefill speed
2.26 s
TTFT
Time to first token
10.04 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
14 days ago
Last verified
Performance
- Ollama · IQ1_S (current)Decode 275.81 · Prefill 1195.7 ·
- Ollama · IQ4_XS Decode 194.74 · Prefill 889.56 ·
- Strata · IQ3_XS Decode 354.49 · Prefill 1856.14 ·
- Strata · Q4_K_S Decode 293.11 · Prefill 1298.77 ·
Core figures
- Decode (avg)
- 275.81 tok/s
- Prefill (avg)
- 1,195.7 tok/s
- TTFT (avg)
- 2.26 s
- VRAM (avg)
- 10.04 GB
- MTP acceptance rate
- —
- TTFB
- 2.21 GB
- Power draw
- 333.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- elephant-1
- Quantization
- IQ1_S
- Framework
- Ollama
- Version
- v0.28
- Context length
- 32768 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 PRO 6000 Blackwell 96GB
- Nominal VRAM
- 96 GB
- Measured VRAM (avg)
- 10.04 GB
- OS
- Windows 11 23H2
- Driver
- 560.94
- CUDA
- 12.8
- Power draw
- 333.6 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
v0.28 · Windows 11 23H2 · CUDA 12.8 · 32768 ctx
275.81 tok/s
Decode
1,195.7 tok/s
Prefill
2.26 s
TTFT
10.04 GB
VRAM
—
MTP
333.6 W
Power draw
L2 batch seed 2026-10-22: Ollama on hw_id=68 running model_id=95 at IQ1_S