Arao AI
Back to search results

DeepSeek-R1-Distill-Qwen-14B · IQ1_S

Start a discussion
NVIDIA RTX 4080 Super16GBllama.cpp v0.31L2 Cross-framework verified

This page aggregates 1 real-world runs of DeepSeek-R1-Distill-Qwen-14B (IQ1_S) on NVIDIA RTX 4080 Super with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

208.08 tok/s

Decode

Decode speed

731.51 tok/s

Prefill

Prefill speed

1.09 s

TTFT

Time to first token

14.45 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 · IQ1_S (current)Decode 208.08 · Prefill 731.51 ·
  2. Strata · IQ2_M Decode 252.15 · Prefill 1022.42 ·

Core figures

Decode (avg)
208.08 tok/s
Prefill (avg)
731.51 tok/s
TTFT (avg)
1.09 s
VRAM (avg)
14.45 GB
MTP acceptance rate
—
TTFB
1.66 GB
Power draw
207.1 W

Configuration

Member-level fields are taken from the most recent run

Model
DeepSeek-R1-Distill-Qwen-14B
Quantization
IQ1_S
Framework
llama.cpp
Version
v0.31
Context length
32768 tokens
Batch size
512
GPU layers
33
Flash Attention
On

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
NVIDIA RTX 4080 Super
Nominal VRAM
16 GB
Measured VRAM (avg)
14.45 GB
OS
Windows 11 23H2
Driver
570.86
CUDA
12.4
Power draw
207.1 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.31 · Windows 11 23H2 · CUDA 12.4 · 32768 ctx

    208.08 tok/s

    Decode

    731.51 tok/s

    Prefill

    1.09 s

    TTFT

    14.45 GB

    VRAM

    —

    MTP

    207.1 W

    Power draw

    L2 batch seed 2026-10-19: llama.cpp on hw_id=20 running model_id=71 at IQ1_S