Arao AI
Back to search results

Qwen3.5-27B · FP16

Start a discussion
NVIDIA RTX PRO 6000 Blackwell 96GB96GBOllama v0.25L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-27B (FP16) on NVIDIA RTX PRO 6000 Blackwell 96GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

79.58 tok/s

Decode

Decode speed

274.78 tok/s

Prefill

Prefill speed

0.69 s

TTFT

Time to first token

91.2 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. llama.cpp · Q4_K_M Decode 181.73 · Prefill 687.5 ·
  2. llama.cpp · Q6_K Decode 133.14 · Prefill 542.78 ·
  3. Ollama · FP16 (current)Decode 79.58 · Prefill 274.78 ·
  4. Ollama · Q3_K_L Decode 177.2 · Prefill 930.23 ·

Core figures

Decode (avg)
79.58 tok/s
Prefill (avg)
274.78 tok/s
TTFT (avg)
0.69 s
VRAM (avg)
91.2 GB
MTP acceptance rate
—
TTFB
0.64 GB
Power draw
301.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-27B
Quantization
FP16
Framework
Ollama
Version
v0.25
Context length
32768 tokens
Batch size
256
GPU layers
28
Flash Attention
On

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)
91.2 GB
OS
Ubuntu 24.04
Driver
560.94
CUDA
12.4
Power draw
301.2 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

    v0.25 · Ubuntu 24.04 · CUDA 12.4 · 32768 ctx

    79.58 tok/s

    Decode

    274.78 tok/s

    Prefill

    0.69 s

    TTFT

    91.2 GB

    VRAM

    —

    MTP

    301.2 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=68 running model_id=50 at FP16