Arao AI
Back to search results

Qwen3-1.7B · Q3_K_M

Start a discussion
NVIDIA RTX 308010GBOllama v0.24L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q3_K_M) on NVIDIA RTX 3080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

123.99 tok/s

Decode

Decode speed

545.14 tok/s

Prefill

Prefill speed

1.89 s

TTFT

Time to first token

4.53 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. Ollama · Q3_K_M (current)Decode 123.99 · Prefill 545.14 ·
  2. Strata · Q3_K_L Decode 204.38 · Prefill 963.09 ·
  3. Strata · Q4_K_S Decode 193.06 · Prefill 868.91 ·

Core figures

Decode (avg)
123.99 tok/s
Prefill (avg)
545.14 tok/s
TTFT (avg)
1.89 s
VRAM (avg)
4.53 GB
MTP acceptance rate
—
TTFB
0.99 GB
Power draw
296.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q3_K_M
Framework
Ollama
Version
v0.24
Context length
4096 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)
4.53 GB
OS
macOS 15.0
Driver
560.94
CUDA
12.4
Power draw
296.8 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

    v0.24 · macOS 15.0 · CUDA 12.4 · 4096 ctx

    123.99 tok/s

    Decode

    545.14 tok/s

    Prefill

    1.89 s

    TTFT

    4.53 GB

    VRAM

    —

    MTP

    296.8 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=44 running model_id=55 at Q3_K_M