elephant-1 · Q4_K_M
This page aggregates 2 real-world runs of elephant-1 (Q4_K_M) on NVIDIA RTX Spark with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
50.55 tok/s
Decode
Decode speed
236.22 tok/s
Prefill
Prefill speed
1.01 s
TTFT
Time to first token
17.6 GB
VRAM
VRAM usage
2
Measured runs
1
Independent sources
Other
Source platforms
13 days ago
Last verified
Performance
- llama.cpp · IQ4_XS Decode 53.68 · Prefill 258.94 ·
- llama.cpp · Q4_K_M (current)Decode 50.55 · Prefill 236.22 ·
- Ollama · Q4_K_M Decode 49.53 · Prefill 221.38 ·
Core figures
- Decode (avg)
- 50.55 tok/s
- Prefill (avg)
- 236.22 tok/s
- TTFT (avg)
- 1.01 s
- VRAM (avg)
- 17.6 GB
- MTP acceptance rate
- —
- TTFB
- 0.41 GB
- Power draw
- 54.05 W
Configuration
Member-level fields are taken from the most recent run
- Model
- elephant-1
- Quantization
- Q4_K_M
- Framework
- llama.cpp
- Version
- v0.50
- Context length
- 2048 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 RTX Spark
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 17.6 GB
- OS
- Ubuntu 24.04
- Driver
- 615.78
- CUDA
- 13.0
- Power draw
- 50.4 W
- Reference price
- $2,399 · updated 2026-10-19
Prices are not live; check the store page
Get started
Original model resources
Base model resources may not match this quantization. Use the verified deployment weights above when available.
Sources & evidence
2 measured records in total, each traceable to its original source
v0.50 · Ubuntu 24.04 · CUDA 13.0 · 2048 ctx
49.66 tok/s
Decode
263.39 tok/s
Prefill
0.17 s
TTFT
17.6 GB
VRAM
—
MTP
50.4 W
Power draw
L2 batch seed 2026-10-22: llama.cpp on hw_id=110 running model_id=95 at Q4_K_M
v0.53 · Ubuntu 24.04 · CUDA 13.0 · 8192 ctx
51.44 tok/s
Decode
209.04 tok/s
Prefill
1.85 s
TTFT
17.6 GB
VRAM
—
MTP
57.7 W
Power draw
L2 batch seed 2026-10-22: llama.cpp on hw_id=110 running model_id=95 at Q4_K_M