Arao AI
Back to search results

Qwen3.8-9B · Q6_K

Start a discussion
NVIDIA RTX Spark128GBOllama v0.46L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q6_K) on NVIDIA RTX Spark with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

34.16 tok/s

Decode

Decode speed

131.09 tok/s

Prefill

Prefill speed

0.38 s

TTFT

Time to first token

21 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

16 days ago

Last verified

Performance

  1. llama.cpp · IQ3_XS Decode 63.8 · Prefill 251.73 ·
  2. llama.cpp · Q4_K_M Decode 51.37 · Prefill 165.51 ·
  3. Ollama · Q4_K_M Decode 45.12 · Prefill 211.38 ·
  4. Ollama · Q6_K (current)Decode 34.16 · Prefill 131.09 ·

Core figures

Decode (avg)
34.16 tok/s
Prefill (avg)
131.09 tok/s
TTFT (avg)
0.38 s
VRAM (avg)
21 GB
MTP acceptance rate
—
TTFB
0.27 GB
Power draw
69.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q6_K
Framework
Ollama
Version
v0.46
Context length
16384 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 RTX Spark
Nominal VRAM
128 GB
Measured VRAM (avg)
21 GB
OS
Ubuntu 24.04
Driver
NVIDIA 590.10
CUDA
13.0
Power draw
69.7 W
Reference price
$2,399 · updated 2026-10-19

Prices are not live; check the store page

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 24.04 · CUDA 13.0 · 16384 ctx

    34.16 tok/s

    Decode

    131.09 tok/s

    Prefill

    0.38 s

    TTFT

    21 GB

    VRAM

    —

    MTP

    69.7 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=110 running model_id=52 at Q6_K