Arao AI
Back to search results

Qwen3-4B · Q2_K

Start a discussion
NVIDIA RTX 308010GBOllama v0.44L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B (Q2_K) on NVIDIA RTX 3080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

102.28 tok/s

Decode

Decode speed

452.09 tok/s

Prefill

Prefill speed

0.59 s

TTFT

Time to first token

6.72 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 131.47 · Prefill 451.18 ·
  2. llama.cpp · Q3_K_L Decode 99.23 · Prefill 538.67 ·
  3. Ollama · IQ2_XS Decode 118.69 · Prefill 621.83 ·
  4. Ollama · Q2_K (current)Decode 102.28 · Prefill 452.09 ·

Core figures

Decode (avg)
102.28 tok/s
Prefill (avg)
452.09 tok/s
TTFT (avg)
0.59 s
VRAM (avg)
6.72 GB
MTP acceptance rate
—
TTFB
0.82 GB
Power draw
308.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B
Quantization
Q2_K
Framework
Ollama
Version
v0.44
Context length
32768 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
NVIDIA RTX 3080
Nominal VRAM
10 GB
Measured VRAM (avg)
6.72 GB
OS
Ubuntu 22.04
Driver
560.94
CUDA
12.4
Power draw
308.5 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

    v0.44 · Ubuntu 22.04 · CUDA 12.4 · 32768 ctx

    102.28 tok/s

    Decode

    452.09 tok/s

    Prefill

    0.59 s

    TTFT

    6.72 GB

    VRAM

    —

    MTP

    308.5 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=44 running model_id=54 at Q2_K