Arao AI
Back to search results

DeepSeek-R1-Distill-Qwen-14B · IQ2_XS

Start a discussion
AMD Radeon RX 9070 XT16GBllama.cpp v0.30L2 Cross-framework verified

This page aggregates 1 real-world runs of DeepSeek-R1-Distill-Qwen-14B (IQ2_XS) on AMD Radeon RX 9070 XT with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

150.94 tok/s

Decode

Decode speed

517.81 tok/s

Prefill

Prefill speed

0.3 s

TTFT

Time to first token

15.2 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · IQ2_XS (current)Decode 150.94 · Prefill 517.81 ·
  2. Ollama · IQ1_S Decode 91.31 · Prefill 484.29 ·

Core figures

Decode (avg)
150.94 tok/s
Prefill (avg)
517.81 tok/s
TTFT (avg)
0.3 s
VRAM (avg)
15.2 GB
MTP acceptance rate
—
TTFB
1.21 GB
Power draw
225.4 W

Configuration

Member-level fields are taken from the most recent run

Model
DeepSeek-R1-Distill-Qwen-14B
Quantization
IQ2_XS
Framework
llama.cpp
Version
v0.30
Context length
4096 tokens
Batch size
256
GPU layers
28
Flash Attention
On

Hardware

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

GPU
AMD Radeon RX 9070 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
15.2 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.12
CUDA
12.6
Power draw
225.4 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

    v0.30 · Ubuntu 22.04 · CUDA 12.6 · 4096 ctx

    150.94 tok/s

    Decode

    517.81 tok/s

    Prefill

    0.3 s

    TTFT

    15.2 GB

    VRAM

    —

    MTP

    225.4 W

    Power draw

    L2 batch seed 2026-10-18: llama.cpp on hw_id=16 running model_id=71 at IQ2_XS