Arao AI
Back to search results

Qwen3.6-35B-A3B · Q3_K_S

Start a discussion
AMD Ryzen AI Max+ 395128GBvLLM v0.53L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.6-35B-A3B (Q3_K_S) on AMD Ryzen AI Max+ 395 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

72.5 tok/s

Decode

Decode speed

334.68 tok/s

Prefill

Prefill speed

1.77 s

TTFT

Time to first token

49.88 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. vLLM · Q3_K_S (current)Decode 72.5 · Prefill 334.68 ·
  2. vLLM · Q6_K Decode 44.31 · Prefill 168.04 ·
  3. Ollama · Q5_K_M Decode 45.61 · Prefill 217.15 ·

Core figures

Decode (avg)
72.5 tok/s
Prefill (avg)
334.68 tok/s
TTFT (avg)
1.77 s
VRAM (avg)
49.88 GB
MTP acceptance rate
—
TTFB
0.58 GB
Power draw
69.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.6-35B-A3B
Quantization
Q3_K_S
Framework
vLLM
Version
v0.53
Context length
32768 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 Ryzen AI Max+ 395
Nominal VRAM
128 GB
Measured VRAM (avg)
49.88 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.11
CUDA
12.8
Power draw
69.1 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

    v0.53 · Ubuntu 22.04 · CUDA 12.8 · 32768 ctx

    72.5 tok/s

    Decode

    334.68 tok/s

    Prefill

    1.77 s

    TTFT

    49.88 GB

    VRAM

    —

    MTP

    69.1 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=24 running model_id=47 at Q3_K_S