Arao AI
Back to search results

Qwen3.6-35B-A3B · Q8_0

Start a discussion
NVIDIA H100 80GB HBM380GBOllama v0.35L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.6-35B-A3B (Q8_0) on NVIDIA H100 80GB HBM3 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

296.95 tok/s

Decode

Decode speed

1,140.84 tok/s

Prefill

Prefill speed

0.25 s

TTFT

Time to first token

76 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

16 days ago

Last verified

Performance

  1. vLLM · IQ4_XS Decode 288.72 · Prefill 1282.53 ·
  2. vLLM · Q3_K_M Decode 355.61 · Prefill 1722.65 ·
  3. Ollama · IQ2_M Decode 321.92 · Prefill 1762.51 ·
  4. Ollama · Q8_0 (current)Decode 296.95 · Prefill 1140.84 ·

Core figures

Decode (avg)
296.95 tok/s
Prefill (avg)
1,140.84 tok/s
TTFT (avg)
0.25 s
VRAM (avg)
76 GB
MTP acceptance rate
—
TTFB
2.38 GB
Power draw
570.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.6-35B-A3B
Quantization
Q8_0
Framework
Ollama
Version
v0.35
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 H100 80GB HBM3
Nominal VRAM
80 GB
Measured VRAM (avg)
76 GB
OS
Ubuntu 24.04
Driver
565.57
CUDA
13.0
Power draw
570.6 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

    v0.35 · Ubuntu 24.04 · CUDA 13.0 · 4096 ctx

    296.95 tok/s

    Decode

    1,140.84 tok/s

    Prefill

    0.25 s

    TTFT

    76 GB

    VRAM

    —

    MTP

    570.6 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=55 running model_id=47 at Q8_0