Arao AI
Back to search results

Qwen3-1.7B · Q3_K_L

Start a discussion
NVIDIA RTX 507012GBOllama v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q3_K_L) on NVIDIA RTX 5070 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

127.9 tok/s

Decode

Decode speed

682.85 tok/s

Prefill

Prefill speed

1.18 s

TTFT

Time to first token

4.67 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · IQ2_M Decode 185.93 · Prefill 658.25 ·
  2. Ollama · Q3_K_L (current)Decode 127.9 · Prefill 682.85 ·
  3. Ollama · Q5_K_M Decode 93.03 · Prefill 365.14 ·
  4. Strata · Q3_K_L Decode 187.58 · Prefill 667.52 ·

Core figures

Decode (avg)
127.9 tok/s
Prefill (avg)
682.85 tok/s
TTFT (avg)
1.18 s
VRAM (avg)
4.67 GB
MTP acceptance rate
—
TTFB
1.02 GB
Power draw
197.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q3_K_L
Framework
Ollama
Version
v0.34
Context length
8192 tokens
Batch size
256
GPU layers
33
Flash Attention
Off

Hardware

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

GPU
NVIDIA RTX 5070
Nominal VRAM
12 GB
Measured VRAM (avg)
4.67 GB
OS
Windows 11 23H2
Driver
565.57
CUDA
12.8
Power draw
197.5 W

Sources & evidence

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

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

    v0.34 · Windows 11 23H2 · CUDA 12.8 · 8192 ctx

    127.9 tok/s

    Decode

    682.85 tok/s

    Prefill

    1.18 s

    TTFT

    4.67 GB

    VRAM

    —

    MTP

    197.5 W

    Power draw

    L2 batch seed 2026-10-10: Ollama on hw_id=18 running model_id=55 at Q3_K_L