Arao AI
Back to search results

Qwen3.5-4B · Q3_K_L

Start a discussion
AMD Radeon RX 9070 XT16GBOllama v0.25L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (Q3_K_L) on AMD Radeon RX 9070 XT with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

133.65 tok/s

Decode

Decode speed

600.15 tok/s

Prefill

Prefill speed

1.07 s

TTFT

Time to first token

8.15 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. llama.cpp · IQ2_M Decode 196.42 · Prefill 767.31 ·
  2. Ollama · FP16 Decode 69.03 · Prefill 237.27 ·
  3. Ollama · Q6_K Decode 103.08 · Prefill 389.31 ·
  4. Ollama · Q3_K_L (current)Decode 133.65 · Prefill 600.15 ·

Core figures

Decode (avg)
133.65 tok/s
Prefill (avg)
600.15 tok/s
TTFT (avg)
1.07 s
VRAM (avg)
8.15 GB
MTP acceptance rate
—
TTFB
1.07 GB
Power draw
307.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
Q3_K_L
Framework
Ollama
Version
v0.25
Context length
8192 tokens
Batch size
256
GPU layers
33
Flash Attention
On

Hardware

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

GPU
AMD Radeon RX 9070 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
8.15 GB
OS
Windows 11 23H2
Driver
amdgpu 6.11
CUDA
N/A
Power draw
307.6 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

    v0.25 · Windows 11 23H2 · CUDA N/A · 8192 ctx

    133.65 tok/s

    Decode

    600.15 tok/s

    Prefill

    1.07 s

    TTFT

    8.15 GB

    VRAM

    —

    MTP

    307.6 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=16 running model_id=48 at Q3_K_L