Arao AI
Back to search results

Qwen2.5-0.5B-Instruct · Q3_K_M

Start a discussion
AMD Radeon AI PRO R970032GBStrata v0.35L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (Q3_K_M) on AMD Radeon AI PRO R9700 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

294.81 tok/s

Decode

Decode speed

1,272.19 tok/s

Prefill

Prefill speed

1.61 s

TTFT

Time to first token

2.81 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_XS Decode 346.96 · Prefill 1652.99 ·
  2. vLLM · Q5_K_S Decode 310.96 · Prefill 1151.48 ·
  3. Strata · Q3_K_M (current)Decode 294.81 · Prefill 1272.19 ·
  4. Strata · Q5_K_M Decode 384.75 · Prefill 2096.67 ·

Core figures

Decode (avg)
294.81 tok/s
Prefill (avg)
1,272.19 tok/s
TTFT (avg)
1.61 s
VRAM (avg)
2.81 GB
MTP acceptance rate
0.65
TTFB
2.36 GB
Power draw
284.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-0.5B-Instruct
Quantization
Q3_K_M
Framework
Strata
Version
v0.35
Context length
32768 tokens
Batch size
512
GPU layers
12
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)
2.81 GB
OS
Ubuntu 24.04
Driver
amdgpu 6.11
CUDA
N/A
Power draw
284.5 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

    v0.35 · Ubuntu 24.04 · CUDA N/A · 32768 ctx

    294.81 tok/s

    Decode

    1,272.19 tok/s

    Prefill

    1.61 s

    TTFT

    2.81 GB

    VRAM

    0.65

    MTP

    284.5 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=79 running model_id=59 at Q3_K_M