Arao AI
Back to search results

Qwen3.8-9B · Q4_K_M

Start a discussion
NVIDIA RTX Spark128GBllama.cpp v0.53L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q4_K_M) on NVIDIA RTX Spark with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

51.37 tok/s

Decode

Decode speed

165.51 tok/s

Prefill

Prefill speed

1.25 s

TTFT

Time to first token

17.6 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 (current)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)
51.37 tok/s
Prefill (avg)
165.51 tok/s
TTFT (avg)
1.25 s
VRAM (avg)
17.6 GB
MTP acceptance rate
—
TTFB
0.41 GB
Power draw
81.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q4_K_M
Framework
llama.cpp
Version
v0.53
Context length
16384 tokens
Batch size
256
GPU layers
99
Flash Attention
Off

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)
17.6 GB
OS
Windows 11 24H2
Driver
NVIDIA 590.10
CUDA
13.0
Power draw
81.8 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

    v0.53 · Windows 11 24H2 · CUDA 13.0 · 16384 ctx

    51.37 tok/s

    Decode

    165.51 tok/s

    Prefill

    1.25 s

    TTFT

    17.6 GB

    VRAM

    —

    MTP

    81.8 W

    Power draw

    L2 batch seed 2026-10-19: llama.cpp on hw_id=110 running model_id=52 at Q4_K_M