Arao AI
Back to search results

DeepSeek-R1-Distill-Qwen-14B · IQ3_S

Start a discussion
NVIDIA RTX Spark128GBOllama v0.27L2 Cross-framework verified

This page aggregates 1 real-world runs of DeepSeek-R1-Distill-Qwen-14B (IQ3_S) on NVIDIA RTX Spark with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

36.95 tok/s

Decode

Decode speed

186.83 tok/s

Prefill

Prefill speed

0.34 s

TTFT

Time to first token

21.5 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 Decode 32.88 · Prefill 122.17 ·
  2. Ollama · IQ3_S (current)Decode 36.95 · Prefill 186.83 ·
  3. Ollama · Q4_K_M Decode 32.3 · Prefill 137.42 ·

Core figures

Decode (avg)
36.95 tok/s
Prefill (avg)
186.83 tok/s
TTFT (avg)
0.34 s
VRAM (avg)
21.5 GB
MTP acceptance rate
—
TTFB
0.3 GB
Power draw
54.2 W

Configuration

Member-level fields are taken from the most recent run

Model
DeepSeek-R1-Distill-Qwen-14B
Quantization
IQ3_S
Framework
Ollama
Version
v0.27
Context length
4096 tokens
Batch size
256
GPU layers
33
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)
21.5 GB
OS
Ubuntu 24.04
Driver
NVIDIA 590.10
CUDA
13.0
Power draw
54.2 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

    v0.27 · Ubuntu 24.04 · CUDA 13.0 · 4096 ctx

    36.95 tok/s

    Decode

    186.83 tok/s

    Prefill

    0.34 s

    TTFT

    21.5 GB

    VRAM

    —

    MTP

    54.2 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=110 running model_id=71 at IQ3_S