Arao AI
Back to search results

Qwen2.5-0.5B-Instruct · Q3_K_M

Start a discussion
NVIDIA RTX 308010GBOllama v0.33L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (Q3_K_M) on NVIDIA RTX 3080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

199.79 tok/s

Decode

Decode speed

1,003.86 tok/s

Prefill

Prefill speed

1.99 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. llama.cpp · IQ2_XS Decode 279.47 · Prefill 1475.5 ·
  2. Ollama · Q3_K_M (current)Decode 199.79 · Prefill 1003.86 ·
  3. Ollama · Q4_K_M Decode 169.99 · Prefill 687.88 ·

Core figures

Decode (avg)
199.79 tok/s
Prefill (avg)
1,003.86 tok/s
TTFT (avg)
1.99 s
VRAM (avg)
2.81 GB
MTP acceptance rate
—
TTFB
1.6 GB
Power draw
309.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-0.5B-Instruct
Quantization
Q3_K_M
Framework
Ollama
Version
v0.33
Context length
16384 tokens
Batch size
256
GPU layers
20
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 3080
Nominal VRAM
10 GB
Measured VRAM (avg)
2.81 GB
OS
macOS 15.0
Driver
555.85
CUDA
12.8
Power draw
309.7 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

    v0.33 · macOS 15.0 · CUDA 12.8 · 16384 ctx

    199.79 tok/s

    Decode

    1,003.86 tok/s

    Prefill

    1.99 s

    TTFT

    2.81 GB

    VRAM

    —

    MTP

    309.7 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=44 running model_id=59 at Q3_K_M