Arao AI
Back to search results

DeepSeek-R1-Distill-Qwen-14B · IQ4_XS

Start a discussion
NVIDIA RTX 309024GBOllama v0.49L2 Cross-framework verified

This page aggregates 1 real-world runs of DeepSeek-R1-Distill-Qwen-14B (IQ4_XS) on NVIDIA RTX 3090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

73.36 tok/s

Decode

Decode speed

312.95 tok/s

Prefill

Prefill speed

1.55 s

TTFT

Time to first token

22.8 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · Q2_K Decode 95.91 · Prefill 524.52 ·
  2. Ollama · IQ4_XS (current)Decode 73.36 · Prefill 312.95 ·
  3. vLLM · Q5_K_M Decode 76.5 · Prefill 573.8 ·
  4. vLLM · Q4_K_M Decode 93.6 · Prefill 702 ·
  5. llama.cpp · Q5_K_M Decode 70.2 · Prefill 526.5 ·
  6. llama.cpp · Q4_K_M Decode 85.9 · Prefill 644.3 ·

Core figures

Decode (avg)
73.36 tok/s
Prefill (avg)
312.95 tok/s
TTFT (avg)
1.55 s
VRAM (avg)
22.8 GB
MTP acceptance rate
—
TTFB
0.59 GB
Power draw
292.5 W

Configuration

Member-level fields are taken from the most recent run

Model
DeepSeek-R1-Distill-Qwen-14B
Quantization
IQ4_XS
Framework
Ollama
Version
v0.49
Context length
4096 tokens
Batch size
512
GPU layers
28
Flash Attention
Off

Hardware

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

GPU
NVIDIA RTX 3090
Nominal VRAM
24 GB
Measured VRAM (avg)
22.8 GB
OS
Ubuntu 24.04
Driver
570.86
CUDA
12.8
Power draw
292.5 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-18

    v0.49 · Ubuntu 24.04 · CUDA 12.8 · 4096 ctx

    73.36 tok/s

    Decode

    312.95 tok/s

    Prefill

    1.55 s

    TTFT

    22.8 GB

    VRAM

    —

    MTP

    292.5 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=2 running model_id=71 at IQ4_XS