Arao AI
Back to search results

Qwen3.6-35B-A3B · Q6_K

Start a discussion
AMD Ryzen AI Max+ 395128GBvLLM v0.47L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.6-35B-A3B (Q6_K) on AMD Ryzen AI Max+ 395 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

44.31 tok/s

Decode

Decode speed

168.04 tok/s

Prefill

Prefill speed

0.2 s

TTFT

Time to first token

75.6 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

16 days ago

Last verified

Performance

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

Core figures

Decode (avg)
44.31 tok/s
Prefill (avg)
168.04 tok/s
TTFT (avg)
0.2 s
VRAM (avg)
75.6 GB
MTP acceptance rate
—
TTFB
0.35 GB
Power draw
52.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.6-35B-A3B
Quantization
Q6_K
Framework
vLLM
Version
v0.47
Context length
32768 tokens
Batch size
32
GPU layers
999
Flash Attention
Off

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)
75.6 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.12
CUDA
12.8
Power draw
52.2 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

    v0.47 · Ubuntu 22.04 · CUDA 12.8 · 32768 ctx

    44.31 tok/s

    Decode

    168.04 tok/s

    Prefill

    0.2 s

    TTFT

    75.6 GB

    VRAM

    —

    MTP

    52.2 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=24 running model_id=47 at Q6_K