Arao AI
Back to search results

Qwen3.8-9B · Q2_K

Start a discussion
NVIDIA RTX 3060 12GB12GBOllama v0.38L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q2_K) on NVIDIA RTX 3060 12GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

64.94 tok/s

Decode

Decode speed

300.22 tok/s

Prefill

Prefill speed

0.34 s

TTFT

Time to first token

11.4 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. Ollama · Q2_K (current)Decode 64.94 · Prefill 300.22 ·
  2. vLLM · IQ3_XS Decode 64.02 · Prefill 298.14 ·
  3. Strata · Q2_K Decode 114.46 · Prefill 600.51 ·
  4. llama.cpp · Q4_K_M Decode 51.1 · Prefill 383.3 ·

Core figures

Decode (avg)
64.94 tok/s
Prefill (avg)
300.22 tok/s
TTFT (avg)
0.34 s
VRAM (avg)
11.4 GB
MTP acceptance rate
—
TTFB
0.52 GB
Power draw
164 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q2_K
Framework
Ollama
Version
v0.38
Context length
4096 tokens
Batch size
512
GPU layers
33
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 3060 12GB
Nominal VRAM
12 GB
Measured VRAM (avg)
11.4 GB
OS
Ubuntu 22.04
Driver
572.83
CUDA
12.6
Power draw
164 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.38 · Ubuntu 22.04 · CUDA 12.6 · 4096 ctx

    64.94 tok/s

    Decode

    300.22 tok/s

    Prefill

    0.34 s

    TTFT

    11.4 GB

    VRAM

    —

    MTP

    164 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=15 running model_id=52 at Q2_K