Arao AI
Back to search results

Qwen3.8-9B · IQ3_XS

Start a discussion
NVIDIA RTX Spark128GBllama.cpp v0.29L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (IQ3_XS) on NVIDIA RTX Spark with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

63.8 tok/s

Decode

Decode speed

251.73 tok/s

Prefill

Prefill speed

0.58 s

TTFT

Time to first token

13.82 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 (current)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 Decode 34.16 · Prefill 131.09 ·

Core figures

Decode (avg)
63.8 tok/s
Prefill (avg)
251.73 tok/s
TTFT (avg)
0.58 s
VRAM (avg)
13.82 GB
MTP acceptance rate
—
TTFB
0.51 GB
Power draw
81.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
IQ3_XS
Framework
llama.cpp
Version
v0.29
Context length
16384 tokens
Batch size
512
GPU layers
99
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)
13.82 GB
OS
Ubuntu 24.04
Driver
NVIDIA 590.10
CUDA
13.0
Power draw
81.6 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

    v0.29 · Ubuntu 24.04 · CUDA 13.0 · 16384 ctx

    63.8 tok/s

    Decode

    251.73 tok/s

    Prefill

    0.58 s

    TTFT

    13.82 GB

    VRAM

    —

    MTP

    81.6 W

    Power draw

    L2 batch seed 2026-10-19: llama.cpp on hw_id=110 running model_id=52 at IQ3_XS