Arao AI
Back to search results

Qwen3.5-4B · Q4_K_M

Start a discussion
AMD Radeon RX 907016GBvLLM v0.41L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (Q4_K_M) on AMD Radeon RX 9070 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

137.14 tok/s

Decode

Decode speed

684.52 tok/s

Prefill

Prefill speed

2.42 s

TTFT

Time to first token

8.99 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_XS Decode 204.13 · Prefill 1113.36 ·
  2. llama.cpp · Q3_K_L Decode 162.78 · Prefill 836.11 ·
  3. vLLM · Q3_K_S Decode 194.22 · Prefill 736.68 ·
  4. vLLM · Q4_K_M (current)Decode 137.14 · Prefill 684.52 ·
  5. llama.cpp · IQ4_XS Decode 127.63 · Prefill 638.8 ·
  6. vLLM · IQ1_S Decode 172.53 · Prefill 556.88 ·
  7. vLLM · IQ3_S Decode 146.59 · Prefill 752.13 ·

Core figures

Decode (avg)
137.14 tok/s
Prefill (avg)
684.52 tok/s
TTFT (avg)
2.42 s
VRAM (avg)
8.99 GB
MTP acceptance rate
—
TTFB
1.1 GB
Power draw
250.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
Q4_K_M
Framework
vLLM
Version
v0.41
Context length
2048 tokens
Batch size
8
GPU layers
999
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
Nominal VRAM
16 GB
Measured VRAM (avg)
8.99 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.12
CUDA
12.4
Power draw
250.8 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

    v0.41 · Ubuntu 22.04 · CUDA 12.4 · 2048 ctx

    137.14 tok/s

    Decode

    684.52 tok/s

    Prefill

    2.42 s

    TTFT

    8.99 GB

    VRAM

    —

    MTP

    250.8 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=21 running model_id=48 at Q4_K_M