Arao AI
Back to search results

Qwen3.6-35B-A3B · Q5_K_S

Start a discussion
NVIDIA RTX PRO 6000 Blackwell 96GB96GBOllama v0.24L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.6-35B-A3B (Q5_K_S) on NVIDIA RTX PRO 6000 Blackwell 96GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

301.35 tok/s

Decode

Decode speed

1,440.97 tok/s

Prefill

Prefill speed

0.67 s

TTFT

Time to first token

68.25 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 · IQ3_XS Decode 319.33 · Prefill 1553.22 ·
  2. Ollama · Q5_K_S (current)Decode 301.35 · Prefill 1440.97 ·

Core figures

Decode (avg)
301.35 tok/s
Prefill (avg)
1,440.97 tok/s
TTFT (avg)
0.67 s
VRAM (avg)
68.25 GB
MTP acceptance rate
—
TTFB
2.41 GB
Power draw
343 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.6-35B-A3B
Quantization
Q5_K_S
Framework
Ollama
Version
v0.24
Context length
4096 tokens
Batch size
256
GPU layers
33
Flash Attention
Off

Hardware

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

GPU
NVIDIA RTX PRO 6000 Blackwell 96GB
Nominal VRAM
96 GB
Measured VRAM (avg)
68.25 GB
OS
Windows 11 23H2
Driver
560.94
CUDA
12.4
Power draw
343 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

    v0.24 · Windows 11 23H2 · CUDA 12.4 · 4096 ctx

    301.35 tok/s

    Decode

    1,440.97 tok/s

    Prefill

    0.67 s

    TTFT

    68.25 GB

    VRAM

    —

    MTP

    343 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=68 running model_id=47 at Q5_K_S