Arao AI
Back to search results

Qwen3.5-4B · Q5_K_S

Start a discussion
NVIDIA RTX 3060 12GB12GBStrata v0.20L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (Q5_K_S) on NVIDIA RTX 3060 12GB with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

113.91 tok/s

Decode

Decode speed

618.95 tok/s

Prefill

Prefill speed

2.48 s

TTFT

Time to first token

9.66 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · IQ3_S Decode 105.18 · Prefill 415.05 ·
  2. Ollama · IQ3_S Decode 95.65 · Prefill 519.99 ·
  3. Ollama · Q3_K_M Decode 97.19 · Prefill 407.59 ·
  4. Strata · Q5_K_S (current)Decode 113.91 · Prefill 618.95 ·
  5. Strata · Q6_K Decode 100.84 · Prefill 413.9 ·
  6. llama.cpp · Q4_K_M Decode 117 · Prefill 877.5 ·

Core figures

Decode (avg)
113.91 tok/s
Prefill (avg)
618.95 tok/s
TTFT (avg)
2.48 s
VRAM (avg)
9.66 GB
MTP acceptance rate
0.54
TTFB
0.91 GB
Power draw
207.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
Q5_K_S
Framework
Strata
Version
v0.20
Context length
4096 tokens
Batch size
512
GPU layers
8
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 3060 12GB
Nominal VRAM
12 GB
Measured VRAM (avg)
9.66 GB
OS
Windows 11 23H2
Driver
560.94
CUDA
12.4
Power draw
207.2 W

Sources & evidence

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

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

    v0.20 · Windows 11 23H2 · CUDA 12.4 · 4096 ctx

    113.91 tok/s

    Decode

    618.95 tok/s

    Prefill

    2.48 s

    TTFT

    9.66 GB

    VRAM

    0.54

    MTP

    207.2 W

    Power draw

    L2 batch seed 2026-10-10: Strata on hw_id=15 running model_id=48 at Q5_K_S