Arao AI
Back to search results

DeepSeek-R1-Distill-Qwen-14B · IQ3_XS

Start a discussion
NVIDIA H100 80GB HBM380GBOllama v0.23L2 Cross-framework verified

This page aggregates 1 real-world runs of DeepSeek-R1-Distill-Qwen-14B (IQ3_XS) on NVIDIA H100 80GB HBM3 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

340.5 tok/s

Decode

Decode speed

1,221.18 tok/s

Prefill

Prefill speed

1.73 s

TTFT

Time to first token

20.33 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 Decode 364.79 · Prefill 1787.53 ·
  3. Ollama · IQ2_XS Decode 291.58 · Prefill 1457.4 ·
  4. Ollama · IQ3_XS (current)Decode 340.5 · Prefill 1221.18 ·

Core figures

Decode (avg)
340.5 tok/s
Prefill (avg)
1,221.18 tok/s
TTFT (avg)
1.73 s
VRAM (avg)
20.33 GB
MTP acceptance rate
—
TTFB
2.72 GB
Power draw
647.6 W

Configuration

Member-level fields are taken from the most recent run

Model
DeepSeek-R1-Distill-Qwen-14B
Quantization
IQ3_XS
Framework
Ollama
Version
v0.23
Context length
8192 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 H100 80GB HBM3
Nominal VRAM
80 GB
Measured VRAM (avg)
20.33 GB
OS
Ubuntu 24.04
Driver
572.83
CUDA
12.8
Power draw
647.6 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

    v0.23 · Ubuntu 24.04 · CUDA 12.8 · 8192 ctx

    340.5 tok/s

    Decode

    1,221.18 tok/s

    Prefill

    1.73 s

    TTFT

    20.33 GB

    VRAM

    —

    MTP

    647.6 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=55 running model_id=71 at IQ3_XS