Arao AI
Back to search results

Qwen3-1.7B · Q3_K_L

Start a discussion
NVIDIA RTX 507012GBStrata v0.50L2 Cross-framework verified

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

187.58 tok/s

Decode

Decode speed

667.52 tok/s

Prefill

Prefill speed

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

Core figures

Decode (avg)
187.58 tok/s
Prefill (avg)
667.52 tok/s
TTFT (avg)
0.7 s
VRAM (avg)
4.67 GB
MTP acceptance rate
0.5
TTFB
1.5 GB
Power draw
255.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q3_K_L
Framework
Strata
Version
v0.50
Context length
16384 tokens
Batch size
1024
GPU layers
15
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)
4.67 GB
OS
Ubuntu 22.04
Driver
565.57
CUDA
12.6
Power draw
255.6 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

    v0.50 · Ubuntu 22.04 · CUDA 12.6 · 16384 ctx

    187.58 tok/s

    Decode

    667.52 tok/s

    Prefill

    0.7 s

    TTFT

    4.67 GB

    VRAM

    0.5

    MTP

    255.6 W

    Power draw

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