Arao AI
Back to search results

Qwen3-4B-Thinking-2507 · IQ4_XS

Start a discussion
NVIDIA RTX 407012GBStrata v0.20L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B-Thinking-2507 (IQ4_XS) on NVIDIA RTX 4070 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

136.2 tok/s

Decode

Decode speed

500.55 tok/s

Prefill

Prefill speed

0.67 s

TTFT

Time to first token

8.32 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 · Q5_K_S Decode 75.85 · Prefill 366.79 ·
  2. Strata · IQ2_XS Decode 167.79 · Prefill 693.81 ·
  3. Strata · IQ4_XS (current)Decode 136.2 · Prefill 500.55 ·

Core figures

Decode (avg)
136.2 tok/s
Prefill (avg)
500.55 tok/s
TTFT (avg)
0.67 s
VRAM (avg)
8.32 GB
MTP acceptance rate
0.71
TTFB
1.09 GB
Power draw
268.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B-Thinking-2507
Quantization
IQ4_XS
Framework
Strata
Version
v0.20
Context length
2048 tokens
Batch size
512
GPU layers
12
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 4070
Nominal VRAM
12 GB
Measured VRAM (avg)
8.32 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
12.4
Power draw
268.2 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

    v0.20 · Ubuntu 22.04 · CUDA 12.4 · 2048 ctx

    136.2 tok/s

    Decode

    500.55 tok/s

    Prefill

    0.67 s

    TTFT

    8.32 GB

    VRAM

    0.71

    MTP

    268.2 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=45 running model_id=57 at IQ4_XS