Arao AI
Back to search results

Qwen3.5-4B · Q3_K_S

Start a discussion
NVIDIA RTX 309024GBllama.cpp v0.46L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (Q3_K_S) on NVIDIA RTX 3090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

115.05 tok/s

Decode

Decode speed

556.74 tok/s

Prefill

Prefill speed

0.12 s

TTFT

Time to first token

7.56 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. llama.cpp · Q2_K Decode 137.84 · Prefill 685.72 ·
  2. llama.cpp · Q3_K_S (current)Decode 115.05 · Prefill 556.74 ·
  3. Ollama · Q3_K_M Decode 101.46 · Prefill 355.86 ·
  4. Ollama · Q5_K_M Decode 80.28 · Prefill 423.81 ·
  5. Ollama · Q3_K_S Decode 109.99 · Prefill 558.1 ·
  6. Ollama · Q8_0 Decode 62.23 · Prefill 337.34 ·
  7. Strata · IQ4_XS Decode 157.12 · Prefill 630.97 ·
  8. llama.cpp · Q5_K_S Decode 139.06 · Prefill 548.16 ·
  9. llama.cpp · Q6_K Decode 108.41 · Prefill 420.36 ·
  10. vLLM · Q5_K_S Decode 129.61 · Prefill 696.02 ·

Core figures

Decode (avg)
115.05 tok/s
Prefill (avg)
556.74 tok/s
TTFT (avg)
0.12 s
VRAM (avg)
7.56 GB
MTP acceptance rate
—
TTFB
0.92 GB
Power draw
255.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
Q3_K_S
Framework
llama.cpp
Version
v0.46
Context length
32768 tokens
Batch size
256
GPU layers
20
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 3090
Nominal VRAM
24 GB
Measured VRAM (avg)
7.56 GB
OS
Ubuntu 24.04
Driver
572.83
CUDA
12.8
Power draw
255.5 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

    v0.46 · Ubuntu 24.04 · CUDA 12.8 · 32768 ctx

    115.05 tok/s

    Decode

    556.74 tok/s

    Prefill

    0.12 s

    TTFT

    7.56 GB

    VRAM

    —

    MTP

    255.5 W

    Power draw

    L2 batch seed 2026-10-19: llama.cpp on hw_id=2 running model_id=48 at Q3_K_S