Arao AI
Back to search results

Qwen3.5-4B · Q6_K

Start a discussion
AMD Radeon RX 9070 XT16GBOllama v0.46L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (Q6_K) on AMD Radeon RX 9070 XT with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

103.08 tok/s

Decode

Decode speed

389.31 tok/s

Prefill

Prefill speed

0.3 s

TTFT

Time to first token

10.5 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

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 (current)Decode 103.08 · Prefill 389.31 ·
  4. Ollama · Q3_K_L Decode 133.65 · Prefill 600.15 ·

Core figures

Decode (avg)
103.08 tok/s
Prefill (avg)
389.31 tok/s
TTFT (avg)
0.3 s
VRAM (avg)
10.5 GB
MTP acceptance rate
—
TTFB
0.82 GB
Power draw
263.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
Q6_K
Framework
Ollama
Version
v0.46
Context length
8192 tokens
Batch size
512
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
AMD Radeon RX 9070 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
10.5 GB
OS
Ubuntu 24.04
Driver
amdgpu 6.12
CUDA
12.6
Power draw
263.8 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-18

    v0.46 · Ubuntu 24.04 · CUDA 12.6 · 8192 ctx

    103.08 tok/s

    Decode

    389.31 tok/s

    Prefill

    0.3 s

    TTFT

    10.5 GB

    VRAM

    —

    MTP

    263.8 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=16 running model_id=48 at Q6_K