Arao AI
Back to search results

Qwen3.5-4B · Q2_K

Start a discussion
NVIDIA RTX 309024GBllama.cpp v0.26L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (Q2_K) on NVIDIA RTX 3090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

137.84 tok/s

Decode

Decode speed

685.72 tok/s

Prefill

Prefill speed

1.34 s

TTFT

Time to first token

6.72 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 (current)Decode 137.84 · Prefill 685.72 ·
  2. llama.cpp · Q3_K_S 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)
137.84 tok/s
Prefill (avg)
685.72 tok/s
TTFT (avg)
1.34 s
VRAM (avg)
6.72 GB
MTP acceptance rate
—
TTFB
1.1 GB
Power draw
313.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
Q2_K
Framework
llama.cpp
Version
v0.26
Context length
16384 tokens
Batch size
256
GPU layers
99
Flash Attention
Off

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)
6.72 GB
OS
Windows 11 24H2
Driver
560.94
CUDA
12.8
Power draw
313.8 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

    v0.26 · Windows 11 24H2 · CUDA 12.8 · 16384 ctx

    137.84 tok/s

    Decode

    685.72 tok/s

    Prefill

    1.34 s

    TTFT

    6.72 GB

    VRAM

    —

    MTP

    313.8 W

    Power draw

    L2 batch seed 2026-10-19: llama.cpp on hw_id=2 running model_id=48 at Q2_K