Arao AI
Back to search results

Qwen3.6-35B-A3B · Q8_0

Start a discussion
NVIDIA H2097GBvLLM v0.27L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.6-35B-A3B (Q8_0) on NVIDIA H20 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

66.61 tok/s

Decode

Decode speed

237.96 tok/s

Prefill

Prefill speed

0.72 s

TTFT

Time to first token

86.62 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 118.48 · Prefill 535.48 ·
  2. vLLM · Q8_0 (current)Decode 66.61 · Prefill 237.96 ·
  3. Ollama · Q3_K_M Decode 90.2 · Prefill 441.65 ·

Core figures

Decode (avg)
66.61 tok/s
Prefill (avg)
237.96 tok/s
TTFT (avg)
0.72 s
VRAM (avg)
86.62 GB
MTP acceptance rate
—
TTFB
0.53 GB
Power draw
305.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.6-35B-A3B
Quantization
Q8_0
Framework
vLLM
Version
v0.27
Context length
2048 tokens
Batch size
8
GPU layers
999
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)
86.62 GB
OS
Ubuntu 24.04
Driver
560.94
CUDA
12.4
Power draw
305.3 W

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 12.4 · 2048 ctx

    66.61 tok/s

    Decode

    237.96 tok/s

    Prefill

    0.72 s

    TTFT

    86.62 GB

    VRAM

    —

    MTP

    305.3 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=56 running model_id=47 at Q8_0