Arao AI
Back to search results

elephant-1 · Q5_K_M

Start a discussion
NVIDIA H2097GBOllama v0.48L2 Cross-framework verified

This page aggregates 1 real-world runs of elephant-1 (Q5_K_M) on NVIDIA H20 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

36.62 tok/s

Decode

Decode speed

154.85 tok/s

Prefill

Prefill speed

1.31 s

TTFT

Time to first token

19.68 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

13 days ago

Last verified

Performance

  1. vLLM · FP16 Decode 25.76 · Prefill 119.08 ·
  2. vLLM · IQ2_XS Decode 68.56 · Prefill 374.49 ·
  3. Ollama · Q5_K_M (current)Decode 36.62 · Prefill 154.85 ·

Core figures

Decode (avg)
36.62 tok/s
Prefill (avg)
154.85 tok/s
TTFT (avg)
1.31 s
VRAM (avg)
19.68 GB
MTP acceptance rate
—
TTFB
0.29 GB
Power draw
354.1 W

Configuration

Member-level fields are taken from the most recent run

Model
elephant-1
Quantization
Q5_K_M
Framework
Ollama
Version
v0.48
Context length
8192 tokens
Batch size
256
GPU layers
20
Flash Attention
On

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
NVIDIA H20
Nominal VRAM
97 GB
Measured VRAM (avg)
19.68 GB
OS
Windows 11 24H2
Driver
572.83
CUDA
12.4
Power draw
354.1 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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-22

    v0.48 · Windows 11 24H2 · CUDA 12.4 · 8192 ctx

    36.62 tok/s

    Decode

    154.85 tok/s

    Prefill

    1.31 s

    TTFT

    19.68 GB

    VRAM

    —

    MTP

    354.1 W

    Power draw

    L2 batch seed 2026-10-22: Ollama on hw_id=56 running model_id=95 at Q5_K_M