Arao AI
Back to search results

Qwen3-1.7B · Q5_K_M

Start a discussion
NVIDIA RTX 507012GBOllama v0.39L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q5_K_M) on NVIDIA RTX 5070 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

93.03 tok/s

Decode

Decode speed

365.14 tok/s

Prefill

Prefill speed

0.83 s

TTFT

Time to first token

5.42 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 Decode 127.9 · Prefill 682.85 ·
  3. Ollama · Q5_K_M (current)Decode 93.03 · Prefill 365.14 ·
  4. Strata · Q3_K_L Decode 187.58 · Prefill 667.52 ·

Core figures

Decode (avg)
93.03 tok/s
Prefill (avg)
365.14 tok/s
TTFT (avg)
0.83 s
VRAM (avg)
5.42 GB
MTP acceptance rate
—
TTFB
0.74 GB
Power draw
250 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q5_K_M
Framework
Ollama
Version
v0.39
Context length
2048 tokens
Batch size
256
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 5070
Nominal VRAM
12 GB
Measured VRAM (avg)
5.42 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
12.8
Power draw
250 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

    v0.39 · Ubuntu 22.04 · CUDA 12.8 · 2048 ctx

    93.03 tok/s

    Decode

    365.14 tok/s

    Prefill

    0.83 s

    TTFT

    5.42 GB

    VRAM

    —

    MTP

    250 W

    Power draw

    L2 batch seed 2026-10-10: Ollama on hw_id=18 running model_id=55 at Q5_K_M