Arao AI
Back to search results

Qwen3.5-4B · Q3_K_M

Start a discussion
NVIDIA RTX 3060 12GB12GBStrata v0.36L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (Q3_K_M) on NVIDIA RTX 3060 12GB with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

112.29 tok/s

Decode

Decode speed

547.52 tok/s

Prefill

Prefill speed

1.86 s

TTFT

Time to first token

7.81 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. Ollama · IQ1_S Decode 110.04 · Prefill 354.52 ·
  2. Strata · Q3_K_M (current)Decode 112.29 · Prefill 547.52 ·
  3. Ollama · IQ2_M Decode 91.19 · Prefill 447.34 ·
  4. Ollama · Q4_K_M Decode 66.59 · Prefill 338.55 ·
  5. llama.cpp · IQ3_S Decode 105.18 · Prefill 415.05 ·
  6. Ollama · IQ3_S Decode 95.65 · Prefill 519.99 ·
  7. Ollama · Q3_K_M Decode 97.19 · Prefill 407.59 ·
  8. Strata · Q5_K_S Decode 113.91 · Prefill 618.95 ·
  9. Strata · Q6_K Decode 100.84 · Prefill 413.9 ·
  10. llama.cpp · Q4_K_M Decode 117 · Prefill 877.5 ·

Core figures

Decode (avg)
112.29 tok/s
Prefill (avg)
547.52 tok/s
TTFT (avg)
1.86 s
VRAM (avg)
7.81 GB
MTP acceptance rate
0.71
TTFB
0.9 GB
Power draw
153.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
Q3_K_M
Framework
Strata
Version
v0.36
Context length
16384 tokens
Batch size
512
GPU layers
5
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)
7.81 GB
OS
Windows 11 24H2
Driver
570.86
CUDA
12.6
Power draw
153.1 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.36 · Windows 11 24H2 · CUDA 12.6 · 16384 ctx

    112.29 tok/s

    Decode

    547.52 tok/s

    Prefill

    1.86 s

    TTFT

    7.81 GB

    VRAM

    0.71

    MTP

    153.1 W

    Power draw

    L2 batch seed 2026-10-19: Strata on hw_id=15 running model_id=48 at Q3_K_M