Arao AI
Back to search results

DeepSeek-R1-Distill-Qwen-14B · Q5_K_S

Start a discussion
NVIDIA H100 80GB HBM380GBvLLM v0.53L2 Cross-framework verified

This page aggregates 1 real-world runs of DeepSeek-R1-Distill-Qwen-14B (Q5_K_S) on NVIDIA H100 80GB HBM3 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

364.79 tok/s

Decode

Decode speed

1,787.53 tok/s

Prefill

Prefill speed

2.34 s

TTFT

Time to first token

28.56 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. vLLM · IQ4_XS Decode 398.24 · Prefill 1414.76 ·
  2. vLLM · Q5_K_S (current)Decode 364.79 · Prefill 1787.53 ·
  3. Ollama · IQ2_XS Decode 291.58 · Prefill 1457.4 ·
  4. Ollama · IQ3_XS Decode 340.5 · Prefill 1221.18 ·

Core figures

Decode (avg)
364.79 tok/s
Prefill (avg)
1,787.53 tok/s
TTFT (avg)
2.34 s
VRAM (avg)
28.56 GB
MTP acceptance rate
—
TTFB
2.92 GB
Power draw
671.3 W

Configuration

Member-level fields are taken from the most recent run

Model
DeepSeek-R1-Distill-Qwen-14B
Quantization
Q5_K_S
Framework
vLLM
Version
v0.53
Context length
2048 tokens
Batch size
16
GPU layers
999
Flash Attention
On

Hardware

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

GPU
NVIDIA H100 80GB HBM3
Nominal VRAM
80 GB
Measured VRAM (avg)
28.56 GB
OS
Ubuntu 22.04
Driver
565.57
CUDA
13.0
Power draw
671.3 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

    v0.53 · Ubuntu 22.04 · CUDA 13.0 · 2048 ctx

    364.79 tok/s

    Decode

    1,787.53 tok/s

    Prefill

    2.34 s

    TTFT

    28.56 GB

    VRAM

    —

    MTP

    671.3 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=55 running model_id=71 at Q5_K_S