Arao AI
Back to search results

Qwen2.5-0.5B-Instruct · IQ2_M

Start a discussion
AMD Radeon RX 7800 XT16GBllama.cpp v0.36L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (IQ2_M) on AMD Radeon RX 7800 XT with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

335.13 tok/s

Decode

Decode speed

1,766.15 tok/s

Prefill

Prefill speed

0.76 s

TTFT

Time to first token

2.65 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. llama.cpp · IQ2_M (current)Decode 335.13 · Prefill 1766.15 ·

Core figures

Decode (avg)
335.13 tok/s
Prefill (avg)
1,766.15 tok/s
TTFT (avg)
0.76 s
VRAM (avg)
2.65 GB
MTP acceptance rate
—
TTFB
2.68 GB
Power draw
310.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-0.5B-Instruct
Quantization
IQ2_M
Framework
llama.cpp
Version
v0.36
Context length
16384 tokens
Batch size
512
GPU layers
99
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 7800 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
2.65 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.11
CUDA
N/A
Power draw
310.1 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

    v0.36 · Ubuntu 22.04 · CUDA N/A · 16384 ctx

    335.13 tok/s

    Decode

    1,766.15 tok/s

    Prefill

    0.76 s

    TTFT

    2.65 GB

    VRAM

    —

    MTP

    310.1 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=31 running model_id=59 at IQ2_M