Arao AI
Back to search results

DeepSeek-R1-Distill-Qwen-14B · IQ3_XS

Start a discussion
AMD Radeon AI PRO R970032GBStrata v0.24L2 Cross-framework verified

This page aggregates 1 real-world runs of DeepSeek-R1-Distill-Qwen-14B (IQ3_XS) on AMD Radeon AI PRO R9700 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

151.48 tok/s

Decode

Decode speed

693.94 tok/s

Prefill

Prefill speed

0.99 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

5 days ago

Last verified

Performance

  1. vLLM · IQ3_S Decode 96.64 · Prefill 451.11 ·
  2. vLLM · Q5_K_M Decode 71.18 · Prefill 263.48 ·
  3. Strata · IQ3_XS (current)Decode 151.48 · Prefill 693.94 ·

Core figures

Decode (avg)
151.48 tok/s
Prefill (avg)
693.94 tok/s
TTFT (avg)
0.99 s
VRAM (avg)
20.33 GB
MTP acceptance rate
0.56
TTFB
1.21 GB
Power draw
295.6 W

Configuration

Member-level fields are taken from the most recent run

Model
DeepSeek-R1-Distill-Qwen-14B
Quantization
IQ3_XS
Framework
Strata
Version
v0.24
Context length
8192 tokens
Batch size
256
GPU layers
5
Flash Attention
On

Hardware

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

GPU
AMD Radeon AI PRO R9700
Nominal VRAM
32 GB
Measured VRAM (avg)
20.33 GB
OS
Ubuntu 24.04
Driver
amdgpu 6.11
CUDA
N/A
Power draw
295.6 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.24 · Ubuntu 24.04 · CUDA N/A · 8192 ctx

    151.48 tok/s

    Decode

    693.94 tok/s

    Prefill

    0.99 s

    TTFT

    20.33 GB

    VRAM

    0.56

    MTP

    295.6 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=79 running model_id=71 at IQ3_XS