Arao AI
Back to search results

Qwen3.6-27B · Q4_K_M

Start a discussion
NVIDIA H2097GBOllama v0.27L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.6-27B (Q4_K_M) on NVIDIA H20 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

32.97 tok/s

Decode

Decode speed

115.23 tok/s

Prefill

Prefill speed

2.19 s

TTFT

Time to first token

48.59 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. vLLM · Q3_K_S Decode 48.48 · Prefill 199.47 ·
  2. Ollama · Q4_K_M (current)Decode 32.97 · Prefill 115.23 ·

Core figures

Decode (avg)
32.97 tok/s
Prefill (avg)
115.23 tok/s
TTFT (avg)
2.19 s
VRAM (avg)
48.59 GB
MTP acceptance rate
—
TTFB
0.26 GB
Power draw
317.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.6-27B
Quantization
Q4_K_M
Framework
Ollama
Version
v0.27
Context length
4096 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)
48.59 GB
OS
Ubuntu 24.04
Driver
572.83
CUDA
12.6
Power draw
317.5 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 2026-10-19

    v0.27 · Ubuntu 24.04 · CUDA 12.6 · 4096 ctx

    32.97 tok/s

    Decode

    115.23 tok/s

    Prefill

    2.19 s

    TTFT

    48.59 GB

    VRAM

    —

    MTP

    317.5 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=56 running model_id=6 at Q4_K_M