Arao AI
Back to search results

Qwen3.6-35B-A3B · Q3_K_M

Start a discussion
NVIDIA H2097GBOllama v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.6-35B-A3B (Q3_K_M) on NVIDIA H20 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

90.2 tok/s

Decode

Decode speed

441.65 tok/s

Prefill

Prefill speed

2.18 s

TTFT

Time to first token

52.08 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 · Q3_K_S Decode 118.48 · Prefill 535.48 ·
  2. vLLM · Q8_0 Decode 66.61 · Prefill 237.96 ·
  3. Ollama · Q3_K_M (current)Decode 90.2 · Prefill 441.65 ·

Core figures

Decode (avg)
90.2 tok/s
Prefill (avg)
441.65 tok/s
TTFT (avg)
2.18 s
VRAM (avg)
52.08 GB
MTP acceptance rate
—
TTFB
0.72 GB
Power draw
302.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.6-35B-A3B
Quantization
Q3_K_M
Framework
Ollama
Version
v0.34
Context length
32768 tokens
Batch size
512
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 H20
Nominal VRAM
97 GB
Measured VRAM (avg)
52.08 GB
OS
Windows 11 24H2
Driver
560.94
CUDA
12.6
Power draw
302.2 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

    v0.34 · Windows 11 24H2 · CUDA 12.6 · 32768 ctx

    90.2 tok/s

    Decode

    441.65 tok/s

    Prefill

    2.18 s

    TTFT

    52.08 GB

    VRAM

    —

    MTP

    302.2 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=56 running model_id=47 at Q3_K_M