Arao AI
Back to search results

DeepSeek-R1-Distill-Qwen-14B · IQ2_M

Start a discussion
AMD Radeon RX 7900 XTX24GBvLLM v0.22L2 Cross-framework verified

This page aggregates 1 real-world runs of DeepSeek-R1-Distill-Qwen-14B (IQ2_M) on AMD Radeon RX 7900 XTX with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

102.61 tok/s

Decode

Decode speed

458.68 tok/s

Prefill

Prefill speed

1.78 s

TTFT

Time to first token

17.39 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · Q3_K_L Decode 85.47 · Prefill 436.48 ·
  2. vLLM · IQ2_M (current)Decode 102.61 · Prefill 458.68 ·

Core figures

Decode (avg)
102.61 tok/s
Prefill (avg)
458.68 tok/s
TTFT (avg)
1.78 s
VRAM (avg)
17.39 GB
MTP acceptance rate
—
TTFB
0.82 GB
Power draw
209 W

Configuration

Member-level fields are taken from the most recent run

Model
DeepSeek-R1-Distill-Qwen-14B
Quantization
IQ2_M
Framework
vLLM
Version
v0.22
Context length
2048 tokens
Batch size
16
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 RX 7900 XTX
Nominal VRAM
24 GB
Measured VRAM (avg)
17.39 GB
OS
Ubuntu 24.04
Driver
amdgpu-pro 24.20
CUDA
12.8
Power draw
209 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

    v0.22 · Ubuntu 24.04 · CUDA 12.8 · 2048 ctx

    102.61 tok/s

    Decode

    458.68 tok/s

    Prefill

    1.78 s

    TTFT

    17.39 GB

    VRAM

    —

    MTP

    209 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=11 running model_id=71 at IQ2_M