elephant-1 · IQ4_XS
This page aggregates 1 real-world runs of elephant-1 (IQ4_XS) on NVIDIA RTX PRO 6000 Blackwell 96GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
194.74 tok/s
Decode
Decode speed
889.56 tok/s
Prefill
Prefill speed
2.05 s
TTFT
Time to first token
16.09 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
13 days ago
Last verified
Performance
- Ollama · IQ1_S Decode 275.81 · Prefill 1195.7 ·
- Ollama · IQ4_XS (current)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)
- 194.74 tok/s
- Prefill (avg)
- 889.56 tok/s
- TTFT (avg)
- 2.05 s
- VRAM (avg)
- 16.09 GB
- MTP acceptance rate
- —
- TTFB
- 1.56 GB
- Power draw
- 372.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- elephant-1
- Quantization
- IQ4_XS
- Framework
- Ollama
- Version
- v0.24
- Context length
- 2048 tokens
- Batch size
- 512
- GPU layers
- 99
- 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)
- 16.09 GB
- OS
- Ubuntu 24.04
- Driver
- 560.94
- CUDA
- 12.6
- Power draw
- 372.8 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
v0.24 · Ubuntu 24.04 · CUDA 12.6 · 2048 ctx
194.74 tok/s
Decode
889.56 tok/s
Prefill
2.05 s
TTFT
16.09 GB
VRAM
—
MTP
372.8 W
Power draw
L2 batch seed 2026-10-22: Ollama on hw_id=68 running model_id=95 at IQ4_XS