Arao AI
Back to search results

Qwen3.8-9B · Q3_K_M

Start a discussion
NVIDIA RTX PRO 6000 Blackwell 96GB96GBOllama v0.46L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q3_K_M) on NVIDIA RTX PRO 6000 Blackwell 96GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

221.75 tok/s

Decode

Decode speed

855.6 tok/s

Prefill

Prefill speed

0.81 s

TTFT

Time to first token

14.95 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 · Q4_K_S Decode 212.78 · Prefill 1065.77 ·
  2. Ollama · Q3_K_M (current)Decode 221.75 · Prefill 855.6 ·
  3. Ollama · Q5_K_M Decode 148.52 · Prefill 762.34 ·

Core figures

Decode (avg)
221.75 tok/s
Prefill (avg)
855.6 tok/s
TTFT (avg)
0.81 s
VRAM (avg)
14.95 GB
MTP acceptance rate
—
TTFB
1.77 GB
Power draw
309.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q3_K_M
Framework
Ollama
Version
v0.46
Context length
8192 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 RTX PRO 6000 Blackwell 96GB
Nominal VRAM
96 GB
Measured VRAM (avg)
14.95 GB
OS
Ubuntu 22.04
Driver
560.94
CUDA
12.8
Power draw
309.5 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

    v0.46 · Ubuntu 22.04 · CUDA 12.8 · 8192 ctx

    221.75 tok/s

    Decode

    855.6 tok/s

    Prefill

    0.81 s

    TTFT

    14.95 GB

    VRAM

    —

    MTP

    309.5 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=68 running model_id=52 at Q3_K_M