Arao AI
Back to search results

DeepSeek-R1-Distill-Qwen-14B · Q5_K_M

Start a discussion
AMD Radeon AI PRO R970032GBvLLM v0.22L2 Cross-framework verified

This page aggregates 1 real-world runs of DeepSeek-R1-Distill-Qwen-14B (Q5_K_M) on AMD Radeon AI PRO R9700 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

71.18 tok/s

Decode

Decode speed

263.48 tok/s

Prefill

Prefill speed

1.98 s

TTFT

Time to first token

29.44 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 (current)Decode 71.18 · Prefill 263.48 ·
  3. Strata · IQ3_XS Decode 151.48 · Prefill 693.94 ·

Core figures

Decode (avg)
71.18 tok/s
Prefill (avg)
263.48 tok/s
TTFT (avg)
1.98 s
VRAM (avg)
29.44 GB
MTP acceptance rate
—
TTFB
0.57 GB
Power draw
235.5 W

Configuration

Member-level fields are taken from the most recent run

Model
DeepSeek-R1-Distill-Qwen-14B
Quantization
Q5_K_M
Framework
vLLM
Version
v0.22
Context length
32768 tokens
Batch size
32
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
AMD Radeon AI PRO R9700
Nominal VRAM
32 GB
Measured VRAM (avg)
29.44 GB
OS
Windows 11 23H2
Driver
amdgpu 6.11
CUDA
N/A
Power draw
235.5 W

Sources & evidence

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

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

    v0.22 · Windows 11 23H2 · CUDA N/A · 32768 ctx

    71.18 tok/s

    Decode

    263.48 tok/s

    Prefill

    1.98 s

    TTFT

    29.44 GB

    VRAM

    —

    MTP

    235.5 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=79 running model_id=71 at Q5_K_M