Arao AI
Back to search results

Qwen3-8B · Q4_K_M

Start a discussion
NVIDIA RTX Spark128GBllama.cpp v0.46L2 Cross-framework verified

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

51.02 tok/s

Decode

Decode speed

251.27 tok/s

Prefill

Prefill speed

1.17 s

TTFT

Time to first token

15.88 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 (current)Decode 51.02 · Prefill 251.27 ·
  2. llama.cpp · Q5_K_M Decode 46.53 · Prefill 174.57 ·
  3. Ollama · Q3_K_L Decode 51.86 · Prefill 267.64 ·
  4. Ollama · Q4_K_M Decode 50.41 · Prefill 184.67 ·

Core figures

Decode (avg)
51.02 tok/s
Prefill (avg)
251.27 tok/s
TTFT (avg)
1.17 s
VRAM (avg)
15.88 GB
MTP acceptance rate
—
TTFB
0.41 GB
Power draw
69.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
Q4_K_M
Framework
llama.cpp
Version
v0.46
Context length
32768 tokens
Batch size
256
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)
15.88 GB
OS
Windows 11 24H2
Driver
NVIDIA 590.10
CUDA
13.0
Power draw
69.8 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

    v0.46 · Windows 11 24H2 · CUDA 13.0 · 32768 ctx

    51.02 tok/s

    Decode

    251.27 tok/s

    Prefill

    1.17 s

    TTFT

    15.88 GB

    VRAM

    —

    MTP

    69.8 W

    Power draw

    L2 batch seed 2026-10-19: llama.cpp on hw_id=110 running model_id=53 at Q4_K_M